Related papers: Error Correction by Paying Attention to Both Acous…
We introduce a new cross-modal fusion technique designed for generative error correction in automatic speech recognition (ASR). Our methodology leverages both acoustic information and external linguistic representations to generate accurate…
Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…
Quantifying the confidence (or conversely the uncertainty) of a prediction is a highly desirable trait of an automatic system, as it improves the robustness and usefulness in downstream tasks. In this paper we investigate confidence…
Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition. When using appropriate modeling units, e.g., byte-pair encoding, these systems are in principle open vocabulary systems. In practice,…
Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…
Automatic Speech Recognition (ASR) plays an important role in speech-based automatic detection of Alzheimer's disease (AD). However, recognition errors could propagate downstream, potentially impacting the detection decisions. Recent…
Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…
In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors should be selected from the n-best list using a language model (LM). However, LMs are usually trained to maximize the likelihood of correct word…
Recognizer Output Voting Error Reduction (ROVER) has been widely used for system combination in automatic speech recognition (ASR). In order to select the most appropriate words to insert at each position in the output transcriptions, some…
Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval…
The transcription quality of automatic speech recognition (ASR) systems degrades significantly when transcribing audios coming from unseen domains. We propose an unsupervised error correction method for unsupervised ASR domain adaption,…
Reverberation negatively impacts the performance of automatic speech recognition (ASR). Prior work on quantifying the effect of reverberation has shown that clarity (C50), a parameter that can be estimated from the acoustic impulse…
In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers…
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system…
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…
Text data is commonly utilized as a primary input to enhance Speech Emotion Recognition (SER) performance and reliability. However, the reliance on human-transcribed text in most studies impedes the development of practical SER systems,…
Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth…
Evaluating automatic speech recognition (ASR) systems is a classical but difficult and still open problem, which often boils down to focusing only on the word error rate (WER). However, this metric suffers from many limitations and does not…
Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…
Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth transcription from the decoded N-best hypotheses. Thanks to the…