Related papers: Effects of Language Modeling on Speech-driven Ques…
Different flavors of transfer learning have shown tremendous impact in advancing research and applications of machine learning. In this work we study the use of a specific family of transfer learning, where the target domain is mapped to…
Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…
Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform…
One of the central skills that language learners need to practice is speaking the language. Currently, students in school do not get enough speaking opportunities and lack conversational practice. Recent advances in speech technology and…
Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…
In recent years, we have observed a rapid advancement in speech language models (SpeechLLMs), catching up with humans' listening and reasoning abilities. SpeechLLMs have demonstrated impressive spoken dialog question-answering (SQA)…
End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words…
Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module,…
When evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. In this paper, we propose a…
Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…
Background: Computational models of speech recognition often assume that the set of target words is already given. This implies that these models do not learn to recognise speech from scratch without prior knowledge and explicit…
Effective spoken dialog systems should facilitate natural interactions with quick and rhythmic timing, mirroring human communication patterns. To reduce response times, previous efforts have focused on minimizing the latency in automatic…
Early detection of Alzheimer's disease from spontaneous speech has emerged as a promising non-invasive screening approach. However, the influence of automatic speech recognition (ASR) quality on downstream clinical language modeling remains…
The amount of freely available systems for automatic speech recognition (ASR) based on neural networks is growing steadily, with equally increasingly reliable predictions. However, the evaluation of trained models is typically exclusively…
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…
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…
Causal language modeling (CLM) serves as the foundational framework underpinning remarkable successes of recent large language models (LLMs). Despite its success, the training approach for next word prediction poses a potential risk of…
This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout…
For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…
Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further…