Related papers: Google USM: Scaling Automatic Speech Recognition B…

Self-supervised learning (SSL) has been dramatically successful not only in monolingual but also in cross-lingual settings. However, since the two settings have been studied individually in general, there has been little research focusing…

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous…

Large Language Models (LLMs) have demonstrated unparalleled effectiveness in various NLP tasks, and integrating LLMs with automatic speech recognition (ASR) is becoming a mainstream paradigm. Building upon this momentum, our research delves…

Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown promise in improving…

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still underperforms on a non-negligible number…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Nowadays, speech is becoming a more common, if not standard, interface to technology. This can be seen in the trend of technology changes over the years. Increasingly, voice is used to control programs, appliances and personal devices…

Speech emotion recognition (SER) has made significant strides with the advent of powerful self-supervised learning (SSL) models. However, the generalization of these models to diverse languages and emotional expressions remains a challenge.…

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…

(Short version of Abstract) This thesis describes an investigation on unsupervised acoustic modeling (UAM) for automatic speech recognition (ASR) in the zero-resource scenario, where only untranscribed speech data is assumed to be…

Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…

We propose Universal target audio Separation (UniSep), addressing the separation task on arbitrary mixtures of different types of audio. Distinguished from previous studies, UniSep is performed on unlimited source domains and unlimited…

Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important…

Conventional end-to-end Automatic Speech Recognition (ASR) models primarily focus on exact transcription tasks, lacking flexibility for nuanced user interactions. With the advent of Large Language Models (LLMs) in speech processing, more…

Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in…

Automatic speech recognition (ASR) systems normally consist of an acoustic model (AM) and a language model (LM). The acoustic model estimates the probability distribution of text given the input speech, while the language model calibrates…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…

In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…