Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

Self-and semi-supervised learning methods have been actively investigated to reduce
labeled training data or enhance model performance. However, these approaches mostly …

State-of-the-art automatic speech recognition (ASR) systems are trained with tens of
thousands of hours of labeled speech data. Human transcription is expensive and time …

In this paper, we explore reducing computational latency of the 2-pass cascaded encoder
model [1]. Specifically, we experiment with reducing the size of the causal 1st-pass and …

In this paper, several works are proposed to address practi-cal challenges for deploying
RNN Transducer (RNN-T) based speech recognition systems. These challenges are …

In Speech Emotion Recognition (SER), textual data is often used alongside audio signals to
address their inherent variability. However, the reliance on human annotated text in most …

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 …

Even though attention-based end-to-end (E2E) automatic speech recognition (ASR) models
have been yielding state-of-the-art recognition accuracy, they still fall behind many of the …

End-to-end models with auto-regressive decoders have shown impressive results for
automatic speech recognition (ASR). These models formulate the sequence-level probability …

Confidence scores are very useful for downstream applications of automatic speech
recognition (ASR) systems. Recent works have proposed using neural networks to learn …