{"type":"ScholarlyArticle","title":"Generating More Audios for End-to-End Spoken Language Understanding","authors":[{"name":"Xuxin Cheng","slug":"xuxin-cheng","given":"Xuxin","family":"Cheng","affiliation":"School of ECE , Peking University , China"},{"name":"Yuexian Zou","slug":"yuexian-zou","given":"Yuexian","family":"Zou","affiliation":"School of ECE , Peking University , China"}],"abstract":"End-to-end spoken language understanding (SLU) aims to directly capture the comprehensive semantics from the given spoken utterance without generating any transcript. Since the transcripts might not always be available, Textless SLU is attracting increasing attention, which could eliminate the need for transcripts but often does not perform as well as SLU models trained with transcripts. In this paper, we focus on the scenarios where the transcripts are not available and propose a framework GMA-SLU to generate more audios according to the labels. In order to alleviate the modality gap between text and audio, two language models are developed and discrete tokens are utilized as a bridge, where the first language model utilizes labels to generate semantic tokens and the second language model adopts these obtained semantic tokens and the acoustic tokens of source audios to generate the synthetic audios. All the experiments are conducted on the monolingual SLU dataset SLURP and the multilingual SLU dataset MINDS-14. Experimental results show that our method outperforms the previous best Textless End-to-end SLU models and can obtain the comparable performance with the models trained with the assistance of the corresponding transcripts.","doi":"10.24963/ijcai.2024/689","url":"https://ijcai.org/proceedings/2024/689","pdf":"https://ijcai.org/proceedings/2024/0689.pdf","markdown":"https://ijcai.org/proceedings/2024/689.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/689","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Natural Language Processing","track":"Main Track","number":689,"pages":{"first":6234,"last":6242},"keywords":["Natural Language Processing: NLP: Dialogue and interactive systems"],"videos":[],"references":[{"position":1,"raw":"[Baevski et al., 2020] Alexei Baevski, Yuhao Zhou, et al. wav2vec 2.0: A framework for self-supervised learning of speech representations. In Proc. of NeurIPS, 2020.","title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","authors":"Alexei Baevski, Yuhao Zhou","year":"2020","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baevski et al., 2022] Alexei Baevski, Wei-Ning Hsu, et al. data2vec: A general framework for self-supervised learn- ing in speech, vision and language. In Proc. of ICML, 2022.","title":"data2vec: A general framework for self-supervised learning in speech, vision and language","authors":"Alexei Baevski, Wei-Ning Hsu","year":"2022","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bastianelli et al., 2020] Emanuele Bastianelli, Andrea Vanzo, et al. SLURP: A spoken language understanding resource package. In Proc. of EMNLP, 2020.","title":"SLURP: A spoken language understanding resource package","authors":"Emanuele Bastianelli, Andrea Vanzo","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Borsos et al., 2022] Zalán Borsos, Raphaël Marinier, et al. Audiolm: a language modeling approach to audio genera- tion, 2022.","title":"Audiolm: a language modeling approach to audio generation","authors":"Borsos","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Brown et al., 2020] Tom B. Brown, Benjamin Mann, et al. Language models are few-shot learners. In Proc. of NeurIPS, 2020.","title":"Language models are few-shot learners","authors":"B Tom, Benjamin Brown, Mann","year":"2020","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chan et al., 2016] William Chan, Navdeep Jaitly, et al. Lis- ten, attend and spell: A neural network for large vo- cabulary conversational speech recognition. In Proc. of ICASSP, 2016.","title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","authors":"William Chan, Navdeep Jaitly","year":"2016","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chang and Chen, 2022] Ya-Hsin Chang and Yun-Nung Chen. Contrastive Learning for Improving ASR Robust- ness in Spoken Language Understanding. In Proc. of In- terspeech, 2022.","title":"Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","authors":"Chang, Chen ; ] Ya-Hsin Chang, Yun-Nung Chen","year":"2022","venue":"Proc. of Interspeech","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2018] Yuan-Ping Chen, Ryan Price, et al. Spo- ken language understanding without speech recognition. In Proc. of ICASSP, 2018.","title":"Spoken language understanding without speech recognition","authors":"Yuan-Ping Chen, Ryan Price","year":"2018","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cheng et al., 2023a] Xuxin Cheng, Bowen Cao, et al. Ml- lmcl: Mutual learning and large-margin contrastive learn- ing for improving asr robustness in spoken language un- derstanding. In Proc. of ACL Findings, 2023.","title":"Mllmcl: Mutual learning and large-margin contrastive learning for improving asr robustness in spoken language understanding","authors":"Cheng","year":"2023","venue":"Proc. of ACL Findings","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cheng et al., 2023b] Xuxin Cheng, Qianqian Dong, et al. M 3 st: Mix at three levels for speech translation. In Proc. of ICASSP, 2023.","title":"M 3 st: Mix at three levels for speech translation","authors":"Cheng","year":"2023","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Cheng et al., 2023c] Xuxin Cheng, Zhihong Zhu, et al. Mrrl: Modifying the reference via reinforcement learning for non-autoregressive joint multiple intent detection and slot filling. In Proc. of EMNLP Findings, 2023.","title":"Mrrl: Modifying the reference via reinforcement learning for non-autoregressive joint multiple intent detection and slot filling","authors":"Cheng","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Chung et al., 2021] Yu-An Chung, Chenguang Zhu, et al. SPLAT: Speech-language joint pre-training for spoken language understanding. In Proc. of NAACL, 2021.","title":"SPLAT: Speech-language joint pre-training for spoken language understanding","authors":"Yu-An Chung, Chenguang Zhu","year":"2021","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Conneau et al., 2022] Alexis Conneau, Ankur Bapna, et al. XTREME-S: Evaluating Cross-lingual Speech Represen- tations. In Proc. of Interspeech, 2022.","title":"XTREME-S: Evaluating Cross-lingual Speech Representations","authors":"Alexis Conneau, Ankur Bapna","year":"2022","venue":"Proc. of Interspeech","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, et al. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. of NAACL, 2019.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Dong et al., 2023a] Linhao Dong, Zhecheng An, et al. CIF- PT: Bridging speech and text representations for spoken language understanding via continuous integrate-and-fire pre-training. In Proc. of ACL Findings, 2023.","title":"CIF-PT: Bridging speech and text representations for spoken language understanding via continuous integrate-and-fire pre-training","authors":"Dong","year":"2023","venue":"Proc. of ACL Findings","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Dong et al., 2023b] Qianqian Dong, Zhiying Huang, et al. Polyvoice: Language models for speech to speech transla- tion, 2023.","title":"Polyvoice: Language models for speech to speech translation","authors":"Dong","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Défossez et al., 2022] Alexandre Défossez, Jade Copet, et al. High fidelity neural audio compression, 2022.","title":"High fidelity neural audio compression","authors":"Alexandre Défossez, Jade Copet","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Fang and Feng, 2023] Qingkai Fang and Yang Feng. Back translation for speech-to-text translation without tran- scripts. In Proc. of ACL, 2023.","title":"Back translation for speech-to-text translation without transcripts","authors":"Feng Fang, Qingkai Fang, Yang Feng","year":"2023","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Garcia et al., 2023] Hugo Flores Garcia, Prem Seethara- man, et al. Vampnet: Music generation via masked acous- tic token modeling. ArXiv preprint, 2023.","title":"Hugo Flores Garcia, Prem Seetharaman, et al. Vampnet: Music generation via masked acoustic token modeling","authors":"Garcia","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Gerz et al., 2021] Daniela Gerz, Pei-Hao Su, et al. Multilin- gual and cross-lingual intent detection from spoken data. In Proc. of EMNLP, 2021.","title":"Multilingual and cross-lingual intent detection from spoken data","authors":"Daniela Gerz, Pei-Hao Su","year":"2021","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Glorot et al., 2011] Xavier Glorot, Antoine Bordes, et al. Deep sparse rectifier neural networks. In Proc. of AIS- TATS, 2011.","title":"Deep sparse rectifier neural networks","authors":"Xavier Glorot, Antoine Bordes","year":"2011","venue":"Proc. of AIS-TATS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Gong et al., 2023] Yuan Gong, Alexander H Liu, et al. Joint audio and speech understanding. In Proc. of ASRU, 2023.","title":"Joint audio and speech understanding","authors":"Yuan Gong, Alexander H Liu","year":"2023","venue":"Proc. of ASRU","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Gulati et al., 2020] Anmol Gulati, James Qin, et al. Con- former: Convolution-augmented Transformer for Speech Recognition. In Proc. of INTERSPEECH, 2020.","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","authors":"Anmol Gulati, James Qin","year":"2020","venue":"Proc. of INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Haghani et al., 2018] Parisa Haghani, Arun Narayanan, et al. From audio to semantics: Approaches to end-to- end spoken language understanding. In 2018 IEEE Spoken Language Technology Workshop (SLT), 2018.","title":"From audio to semantics: Approaches to end-toend spoken language understanding","authors":"Parisa Haghani, Arun Narayanan","year":"2018","venue":"IEEE Spoken Language Technology Workshop (SLT)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Hakkani-Tür et al., 2006] Dilek Hakkani-Tür, Frédéric Béchet, et al. Beyond asr 1-best: Using word confusion networks in spoken language understanding. Computer Speech & Language, 2006.","title":"Beyond asr 1-best: Using word confusion networks in spoken language understanding","authors":"Dilek Hakkani-Tür, Frédéric Béchet","year":"2006","venue":"Computer Speech & Language","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[He and Garner, 2023] Mutian He and Philip N. Garner. Can ChatGPT Detect Intent? Evaluating Large Language Mod- els for Spoken Language Understanding. In Proc. of Inter- speech, 2023.","title":"Can ChatGPT Detect Intent? Evaluating Large Language Models for Spoken Language Understanding","authors":"Garner He, Mutian He, Philip N Garner","year":"2023","venue":"Proc. of Interspeech","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Hsu et al., 2021] Wei-Ning Hsu, Benjamin Bolte, et al. Hu- bert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transac- tions on Audio, Speech, and Language Processing, 2021.","title":"Hubert: Self-supervised speech representation learning by masked prediction of hidden units","authors":"Wei-Ning Hsu, Benjamin Bolte","year":"2021","venue":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Huang et al., 2022] Zhiqi Huang, Milind Rao, et al. MTL- SLT: Multi-task learning for spoken language tasks. In Proceedings of the 4th Workshop on NLP for Conversa- tional AI, 2022.","title":"MTL-SLT: Multi-task learning for spoken language tasks","authors":"Huang","year":"2022","venue":"Proceedings of the 4th Workshop on NLP for Conversational AI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Proc. of ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Lee et al., 2012] Hung-yi Lee, Chia-ping Chen, et al. Inte- grating recognition and retrieval with relevance feedback for spoken term detection. IEEE transactions on audio, speech, and language processing, 2012.","title":"Integrating recognition and retrieval with relevance feedback for spoken term detection","authors":"Lee","year":"2012","venue":"IEEE transactions on audio, speech, and language processing","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Lee et al., 2022] Ann Lee, Peng-Jen Chen, et al. Direct speech-to-speech translation with discrete units. In Proc. of ACL, 2022.","title":"Direct speech-to-speech translation with discrete units","authors":"Ann Lee, Peng-Jen Chen","year":"2022","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Lewis et al., 2020] Mike Lewis, Yinhan Liu, et al. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proc. of ACL, 2020.","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","authors":"Mike Lewis, Yinhan Liu","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Liu et al., 2019] Yinhan Liu, Myle Ott, et al. Roberta: A robustly optimized bert pretraining approach. ArXiv preprint, 2019.","title":"Roberta: A robustly optimized bert pretraining approach","authors":"Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Lozhkov, 2022] Anton Lozhkov. Hugging Face: anton- l/xtreme s xlsr 300m minds14. https://huggingface.co/ anton-l/xtreme s xlsr 300m minds14, 2022.","title":"Anton Lozhkov. Hugging Face: antonl/xtreme s xlsr 300m minds14","authors":"Lozhkov","year":"2022","venue":null,"doi":null,"url":"https://huggingface.co/anton-l/xtremesxlsr300mminds14","internal_url":null},{"position":35,"raw":"[Ma et al., 2023a] Yubo Ma, Yixin Cao, et al. Large lan- guage model is not a good few-shot information extractor, but a good reranker for hard samples! In Proc. of EMNLP Findings, 2023.","title":"Large language model is not a good few-shot information extractor, but a good reranker for hard samples!","authors":"Ma","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Ma et al., 2023b] Yukun Ma, Trung Hieu Nguyen, et al. Auxiliary pooling layer for spoken language understand- ing. In Proc. of ICASSP, 2023.","title":"Auxiliary pooling layer for spoken language understanding","authors":"Ma","year":"2023","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Mai et al., 2020] Sijie Mai, Haifeng Hu, et al. Modality to modality translation: An adversarial representation learn- ing and graph fusion network for multimodal fusion. In Proc. of AAAI, 2020.","title":"Modality to modality translation: An adversarial representation learning and graph fusion network for multimodal fusion","authors":"Sijie Mai, Haifeng Hu","year":"2020","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Morbini et al., 2012] Fabrizio Morbini, Kartik Audhkhasi, et al. A reranking approach for recognition and classifica- tion of speech input in conversational dialogue systems. In 2012 IEEE Spoken Language Technology Workshop (SLT), 2012.","title":"A reranking approach for recognition and classification of speech input in conversational dialogue systems","authors":"Fabrizio Morbini, Kartik Audhkhasi","year":"2012","venue":"IEEE Spoken Language Technology Workshop (SLT)","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[OpenAI, 2023] OpenAI. Chatgpt. https://chat.openai.com, 2023.","title":"OpenAI. Chatgpt","authors":"Openai","year":"2023","venue":null,"doi":null,"url":"https://chat.openai.com","internal_url":null},{"position":40,"raw":"[Peng et al., 2022] Yifan Peng, Siddharth Dalmia, et al. Branchformer: Parallel mlp-attention architectures to cap- ture local and global context for speech recognition and understanding. In Proc. of ICML, 2022.","title":"Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","authors":"Yifan Peng, Siddharth Dalmia","year":"2022","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Polyak et al., 2021] Adam Polyak, Yossi Adi, et al. Speech resynthesis from discrete disentangled self-supervised rep- resentations. In Proc. of INTERSPEECH, 2021.","title":"Speech resynthesis from discrete disentangled self-supervised representations","authors":"Adam Polyak, Yossi Adi","year":"2021","venue":"Proc. of INTERSPEECH","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Ravanelli et al., 2021] Mirco Ravanelli, Titouan Parcollet, et al. Speechbrain: A general-purpose speech toolkit. ArXiv preprint, 2021.","title":"Speechbrain: A general-purpose speech toolkit","authors":"Mirco Ravanelli, Titouan Parcollet","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Ren et al., 2020] Yi Ren, Chenxu Hu, et al. Fastspeech 2: Fast and high-quality end-to-end text to speech. In Proc. of ICLR, 2020.","title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","authors":"Yi Ren, Chenxu Hu","year":"2020","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Ren et al., 2023] Yong Ren, Tao Wang, et al. Fewer-token neural speech codec with time-invariant codes, 2023.","title":"Fewer-token neural speech codec with time-invariant codes","authors":"Yong Ren, Tao Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Rubenstein et al., 2023] Paul K. Rubenstein, Chulayuth Asawaroengchai, et al. Audiopalm: A large language model that can speak and listen, 2023.","title":"Audiopalm: A large language model that can speak and listen","authors":"Paul K Rubenstein, Chulayuth Asawaroengchai","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Seo et al., 2022] Seunghyun Seo, Donghyun Kwak, et al. Integration of pre-trained networks with continuous token interface for end-to-end spoken language understanding. In Proc. of ICASSP, 2022. [Serdyuk et al., 2018]","title":"Integration of pre-trained networks with continuous token interface for end-to-end spoken language understanding","authors":"Seunghyun Seo, Donghyun Kwak","year":"2018","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"Dmitriy Serdyuk, Yongqiang Wang, et al. Towards end-to-end spoken language understanding. In Proc. of ICASSP, 2018.","title":"Towards end-to-end spoken language understanding","authors":"Dmitriy Serdyuk, Yongqiang Wang","year":"2018","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Touvron et al., 2023] Hugo Touvron, Louis Martin, et al. Llama 2: Open foundation and fine-tuned chat models. ArXiv preprint, 2023.","title":"Llama 2: Open foundation and fine-tuned chat models","authors":"Touvron","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Tur and De Mori, 2011] Gokhan Tur and Renato De Mori. Spoken language understanding: Systems for extracting semantic information from speech. John Wiley & Sons, 2011.","title":"Spoken language understanding: Systems for extracting semantic information from speech","authors":"De Tur, ; Mori, Gokhan Tur, Renato De Mori","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Vaessen and Van Leeuwen, 2022] Nik Vaessen and David A Van Leeuwen. Fine-tuning wav2vec2 for speaker recogni- tion. In Proc. of ICASSP, 2022.","title":"Fine-tuning wav2vec2 for speaker recognition","authors":"Van Vaessen, Nik Leeuwen, David A Vaessen, Van Leeuwen","year":"2022","venue":"Proc. of ICASSP","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, et al. Attention is all you need. In Proc. of NeurIPS, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer","year":"2017","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Wang et al., 2005] Ye-Yi Wang, Li Deng, et al. Spoken lan- guage understanding. IEEE Signal Processing Magazine, 2005.","title":"Spoken language understanding","authors":"Wang","year":"2005","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Wang et al., 2021] Yingzhi Wang, Abdelmoumene Boumadane, et al. A fine-tuned wav2vec 2.0/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding. ArXiv preprint, 2021.","title":"Yingzhi Wang, Abdelmoumene Boumadane, et al. A fine-tuned wav2vec 2.0/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding","authors":"Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Wang et al., 2023a] Chengyi Wang, Sanyuan Chen, et al. Neural codec language models are zero-shot text to speech synthesizers, 2023.","title":"Neural codec language models are zero-shot text to speech synthesizers","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Wang et al., 2023b] Qing Wang, Jun Du, et al. A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detec- tion. IEEE/ACM Transactions on Audio, Speech, and Lan- guage Processing, 2023.","title":"A four-stage data augmentation approach to resnet-conformer based acoustic modeling for sound event localization and detection","authors":"Wang","year":"2023","venue":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Yang et al., 2023] Dongchao Yang, Songxiang Liu, et al. Hifi-codec: Group-residual vector quantization for high fi- delity audio codec, 2023.","title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","authors":"Yang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Zeghidour et al., 2021] Neil Zeghidour, Neil, Luebs, et al. Soundstream: An end-to-end neural audio codec. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021.","title":"Soundstream: An end-to-end neural audio codec","authors":"Neil Zeghidour, Neil, Luebs","year":"2021","venue":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Zhang et al., 2021] Chen Zhang, Xu Tan, et al. Uwspeech: Speech to speech translation for unwritten languages. In Proc. of AAAI, 2021.","title":"Uwspeech: Speech to speech translation for unwritten languages","authors":"Chen Zhang, Xu Tan","year":"2021","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Zhang et al., 2023a] Dong Zhang, Shimin Li, et al. SpeechGPT: Empowering large language models with in- trinsic cross-modal conversational abilities. In Proc. of EMNLP Findings, 2023.","title":"SpeechGPT: Empowering large language models with intrinsic cross-modal conversational abilities","authors":"Zhang","year":"2023","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Zhang et al., 2023b] Xin Zhang, Dong Zhang, et al. Speechtokenizer: Unified speech tokenizer for speech large language models, 2023.","title":"Speechtokenizer: Unified speech tokenizer for speech large language models","authors":"Zhang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Zhu et al., 2023] Zhihong Zhu, Xuxin Cheng, et al. To- wards unified spoken language understanding decoding via label-aware compact linguistics representations. In Proc. of ACL Findings, 2023.","title":"Towards unified spoken language understanding decoding via label-aware compact linguistics representations","authors":"Zhihong Zhu, Xuxin Cheng","year":"2023","venue":"Proc. of ACL Findings","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}