Related papers: Utterance-Wise Meeting Transcription System Using …
Continuous speech separation using a microphone array was shown to be promising in dealing with the speech overlap problem in natural conversation transcription. This paper proposes VarArray, an array-geometry-agnostic speech separation…
Benefiting from massive and diverse data sources, speech foundation models exhibit strong generalization and knowledge transfer capabilities to a wide range of downstream tasks. However, a limitation arises from their exclusive handling of…
Strong representations of target speakers can help extract important information about speakers and detect corresponding temporal regions in multi-speaker conversations. In this study, we propose a neural architecture that simultaneously…
The front-end module in multi-channel automatic speech recognition (ASR) systems mainly use microphone array techniques to produce enhanced signals in noisy conditions with reverberation and echos. Recently, neural network (NN) based…
Speech separation has been shown effective for multi-talker speech recognition. Under the ad hoc microphone array setup where the array consists of spatially distributed asynchronous microphones, additional challenges must be overcome as…
Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels. Recent advances have shown that joint ASR and SD models can learn to…
We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via…
Speaker-attributed automatic speech recognition (ASR) in multi-speaker environments remains a major challenge. While some approaches achieve strong performance when fine-tuned on specific domains, few systems generalize well across…
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array…
This paper describes the TSUP team's submission to the ISCSLP 2022 conversational short-phrase speaker diarization (CSSD) challenge which particularly focuses on short-phrase conversations with a new evaluation metric called conversational…
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in…
Speaker diarization remains challenging due to the need for structured speaker representations, efficient modeling, and robustness to varying conditions. We propose a performant, compact diarization framework that integrates conformer…
Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants…
Multi-talker overlapped speech recognition remains a significant challenge, requiring not only speech recognition but also speaker diarization tasks to be addressed. In this paper, to better address these tasks, we first introduce speaker…
We present a Conformer-based end-to-end neural diarization (EEND) model that uses both acoustic input and features derived from an automatic speech recognition (ASR) model. Two categories of features are explored: features derived directly…
The objective of this work is effective speaker diarisation using multi-scale speaker embeddings. Typically, there is a trade-off between the ability to recognise short speaker segments and the discriminative power of the embedding,…
Automatic speaker diarization techniques typically involve a two-stage processing approach where audio segments of fixed duration are converted to vector representations in the first stage. This is followed by an unsupervised clustering of…
In practical settings, a speaker recognition system needs to identify a speaker given a short utterance, while the enrollment utterance may be relatively long. However, existing speaker recognition models perform poorly with such short…
This paper presents a complete hardware and software pipeline for real-time speech enhancement in noisy and reverberant conditions. The device consists of a microphone array and a camera mounted on eyeglasses, connected to an embedded…
Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw…