相关论文: MIMO-SPEECH: End-to-End Multi-Channel Multi-Speake…

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to…

Deep learning speech separation algorithms have achieved great success in improving the quality and intelligibility of separated speech from mixed audio. Most previous methods focused on generating a single-channel output for each of the…

Recently, many deep learning based beamformers have been proposed for multi-channel speech separation. Nevertheless, most of them rely on extra cues known in advance, such as speaker feature, face image or directional information. In this…

All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single neural network to transduce audio to word sequences have been shown to achieve state-of-the-art results on several tasks. In this work, we examine the…

Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous…

Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk speech separation, the applications to real-world are still an open issue. Two main…

In this paper, we make the explicit connection between image segmentation methods and end-to-end diarization methods. From these insights, we propose a novel, fully end-to-end diarization model, EEND-M2F, based on the Mask2Former…

Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU). Through the term end-to-end, one considers the use of a single model optimized to extract semantic information…

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

End-to-end (E2E) systems have played a more and more important role in automatic speech recognition (ASR) and achieved great performance. However, E2E systems recognize output word sequences directly with the input acoustic feature, which…

Automatic speech recognition (ASR) of multi-channel multi-speaker overlapped speech remains one of the most challenging tasks to the speech community. In this paper, we look into this challenge by utilizing the location information of…

End-to-end models with large capacity have significantly improved multilingual automatic speech recognition, but their computation cost poses challenges for on-device applications. We propose a streaming truly multilingual Conformer…

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

Joint optimization of multi-channel front-end and automatic speech recognition (ASR) has attracted much interest. While promising results have been reported for various tasks, past studies on its meeting transcription application were…

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…

We propose an end-to-end joint optimization framework of a multi-channel neural speech extraction and deep acoustic model without mel-filterbank (FBANK) extraction for overlapped speech recognition. First, based on a multi-channel…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is typically unknown. To cope with this, we extend an iterative…

In recent years, there have been studies to further improve the end-to-end neural speaker diarization (EEND) systems. This letter proposes the EEND-DEMUX model, a novel framework utilizing demultiplexed speaker embeddings. In this work, we…

Current multi-channel speech enhancement systems mainly adopt single-output architecture, which face significant challenges in preserving spatio-temporal signal integrity during multiple-input multiple-output (MIMO) processing. To address…