Related papers: Listening to Multi-talker Conversations: Modular a…
Speech separation with several speakers is a challenging task because of the non-stationarity of the speech and the strong signal similarity between interferent sources. Current state-of-the-art solutions can separate well the different…
End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…
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…
Speaker individuality information is among the most critical elements within speech signals. By thoroughly and accurately modeling this information, it can be utilized in various intelligent speech applications, such as speaker recognition,…
Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior…
We consider the problem of audio voice separation for binaural applications, such as earphones and hearing aids. While today's neural networks perform remarkably well (separating $4+$ sources with 2 microphones) they assume a known or fixed…
Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its…
A major drawback of supervised speech separation (SSep) systems is their reliance on synthetic data, leading to poor real-world generalization. Mixture invariant training (MixIT) was proposed as an unsupervised alternative that uses real…
Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research…
This paper details our speaker diarization system designed for multi-domain, multi-microphone casual conversations. The proposed diarization pipeline uses weighted prediction error (WPE)-based dereverberation as a front end, then applies…
This paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech…
Emotion recognition in multi-speaker conversations faces significant challenges due to speaker ambiguity and severe class imbalance. We propose a novel framework that addresses these issues through three key innovations: (1) a speaker…
Speaker identification in noisy audio recordings, specifically those from collaborative learning environments, can be extremely challenging. There is a need to identify individual students talking in small groups from other students talking…
Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components.…
This paper proposes a serialized multi-layer multi-head attention for neural speaker embedding in text-independent speaker verification. In prior works, frame-level features from one layer are aggregated to form an utterance-level…
Automatic Speech Recognition systems have made significant progress with large-scale pre-trained models. However, most current systems focus solely on transcribing the speech without identifying speaker roles, a function that is critical…
Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases.…
This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation in recording equipment, noise conditions, and conversational…
Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous…
The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference samples. In this work, we investigate different speaker…