English
Related papers

Related papers: Phonetic-assisted Multi-Target Units Modeling for …

200 papers

Parameter-efficient (PE) methods (like Prompts or Adapters) for adapting pre-trained language models (PLM) to downstream tasks have been popular recently. However, hindrances still prevent these methods from reaching their full potential.…

Computation and Language · Computer Science 2024-05-31 Shih-Cheng Huang , Shih-Heng Wang , Min-Han Shih , Saurav Sahay , Hung-yi Lee

The INTERSPEECH 2025 Challenge on Multilingual Conversational Speech Language Models (MLC-SLM) promotes multilingual conversational ASR with large language models (LLMs). Our previous SHNU-mASR system adopted a competitive…

Computation and Language · Computer Science 2026-02-03 Yuxiang Mei , Dongxing Xu , Jiaen Liang , Yanhua Long

Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between…

Computation and Language · Computer Science 2022-03-24 Zexun Wang , Yuquan Le , Yi Zhu , Yuming Zhao , Mingchao Feng , Meng Chen , Xiaodong He

Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce…

Machine Learning · Computer Science 2024-06-26 Van Tung Pham , Yist Lin , Tao Han , Wei Li , Jun Zhang , Lu Lu , Yuxuan Wang

The attention-based encoder-decoder modeling paradigm has achieved promising results on a variety of speech processing tasks like automatic speech recognition (ASR), text-to-speech (TTS) and among others. This paradigm takes advantage of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-07-23 Shi-Yan Weng , Berlin Chen

End-to-end speech recognition models are improved by incorporating external text sources, typically by fusion with an external language model. Such language models have to be retrained whenever the corpus of interest changes. Furthermore,…

Computation and Language · Computer Science 2023-03-21 Bolaji Yusuf , Aditya Gourav , Ankur Gandhe , Ivan Bulyko

Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…

Audio and Speech Processing · Electrical Eng. & Systems 2017-11-15 Markus Müller , Sebastian Stüker , Alex Waibel

Neural network pruning compresses automatic speech recognition (ASR) models effectively. However, in multilingual ASR, language-agnostic pruning may lead to severe performance drops on some languages because language-agnostic pruning masks…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-02 Mu Yang , Andros Tjandra , Chunxi Liu , David Zhang , Duc Le , Ozlem Kalinli

Automatic speech recognition (ASR) has reached a level of accuracy in recent years, that even outperforms humans in transcribing speech to text. Nevertheless, all current ASR approaches show a certain weakness against ambient noise. To…

Sound · Computer Science 2023-12-22 Christopher Simic , Tobias Bocklet

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature representations. Using automatic speech recognition (ASR) as…

Computation and Language · Computer Science 2023-11-28 Shuyue Stella Li , Beining Xu , Xiangyu Zhang , Hexin Liu , Wenhan Chao , Leibny Paola Garcia

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce…

Machine Learning · Computer Science 2026-03-18 Zijin Gu , Tatiana Likhomanenko , He Bai , Erik McDermott , Ronan Collobert , Navdeep Jaitly

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled…

Computation and Language · Computer Science 2023-06-06 Ramon Sanabria , Ondrej Klejch , Hao Tang , Sharon Goldwater

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…

Audio and Speech Processing · Electrical Eng. & Systems 2019-06-14 Chris Larson , Tarek Lahlou , Diana Mingels , Zachary Kulis , Erik Mueller

Recent language model-based text-to-speech (TTS) frameworks demonstrate scalability and in-context learning capabilities. However, they suffer from robustness issues due to the accumulation of errors in speech unit predictions during…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Kun Zhou , Shengkui Zhao , Yukun Ma , Chong Zhang , Hao Wang , Dianwen Ng , Chongjia Ni , Nguyen Trung Hieu , Jia Qi Yip , Bin Ma

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Artificial Intelligence · Computer Science 2021-03-19 Md Akmal Haidar , Chao Xing , Mehdi Rezagholizadeh

Automatic Speech Recognition (ASR) models have achieved remarkable accuracy in general settings, yet their performance often degrades in domain-specific applications due to data mismatch and linguistic variability. This challenge is…

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of…

Computation and Language · Computer Science 2021-07-14 Hang Le , Juan Pino , Changhan Wang , Jiatao Gu , Didier Schwab , Laurent Besacier

End-to-end (E2E) modeling is advantageous for automatic speech recognition (ASR) especially for Japanese since word-based tokenization of Japanese is not trivial, and E2E modeling is able to model character sequences directly. This paper…

Computation and Language · Computer Science 2021-06-10 Shigeki Karita , Yotaro Kubo , Michiel Adriaan Unico Bacchiani , Llion Jones

Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-29 Li Fu , Xiaoxiao Li , Libo Zi

Personalized speech enhancement (PSE) models utilize additional cues, such as speaker embeddings like d-vectors, to remove background noise and interfering speech in real-time and thus improve the speech quality of online video conferencing…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-20 Sefik Emre Eskimez , Takuya Yoshioka , Huaming Wang , Xiaofei Wang , Zhuo Chen , Xuedong Huang