Related papers: Employing Subsequence Matching in Audio Data Proce…
Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…
ASR has been shown to achieve great performance recently. However, most of them rely on massive paired data, which is not feasible for low-resource languages worldwide. This paper investigates how to learn directly from unpaired phone…
Although modern automatic speech recognition (ASR) systems can achieve high performance, they may produce errors that weaken readers' experience and do harm to downstream tasks. To improve the accuracy and reliability of ASR hypotheses, we…
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…
Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching…
Automatic Speech Recognition (ASR) systems have been evolving quickly and reaching human parity in certain cases. The systems usually perform pretty well on reading style and clean speech, however, most of the available systems suffer from…
The dictionary matching problem is to locate occurrences of any pattern among a set of patterns in a given text. Massive data sets abound and at the same time, there are many settings in which working space is extremely limited. We…
Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…
Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…
Most of the previous approaches to lyrics-to-audio alignment used a pre-developed automatic speech recognition (ASR) system that innately suffered from several difficulties to adapt the speech model to individual singers. A significant…
Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In language this interface is given by tokens; in audio, it must be learned. Existing audio…
Audio fingerprinting techniques have seen great advances in recent years, enabling accurate and fast audio retrieval even in conditions when the queried audio sample has been highly deteriorated or recorded in noisy conditions. Expectedly,…
Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…
Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and…
Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…
An ideal audio retrieval system efficiently and robustly recognizes a short query snippet from an extensive database. However, the performance of well-known audio fingerprinting systems falls short at high signal distortion levels. This…
Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a…
Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…
Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains. One example is systems that interact with users, log user actions and behaviour, and make recommendations of items of potential…
Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…