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 …

Speech summarization is typically performed by using a cascade of speech recognition and
text summarization models. End-to-end modeling of speech summarization models is …

Long-content automatic speech recognition (ASR) has obtained increasing interest in recent
years, as it captures the relationship among consecutive historical utterances while …

Automatic Speech Recognition (ASR) in conversational settings presents unique
challenges, including extracting relevant contextual information from previous …

Typical automatic speech recognition (ASR) systems are built to recognize independent
utterances without using the cross-utterance context. However, the context over multiple …

Current ASR systems are mainly trained and evaluated at the utterance level. Long range
cross utterance context can be incorporated. A key task is to derive a suitable compact …

Traditional automatic speech recognition (ASR) systems usually focus on individual
utterances, without considering long-form speech with useful historical information, which is …

Self-supervised pre-trained transformers have improved the state of the art on a variety of
speech tasks. Due to the quadratic time and space complexity of self-attention, they usually …

Leveraging context information is an intuitive idea to improve performance on
conversational automatic speech recognition (ASR). Previous works usually adopt …

End-to-end speech summarization has been shown to improve performance over cascade
baselines. However, such models are difficult to train on very large inputs (dozens of …