End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning
This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from clean speech. This proposed framework does not require any parallel non-overlapped speech materials and is independent of the number of speakers. Our experimental results on overlapped speech datasets show that joint conditioning on speaker embeddings and transfer learning significantly improves the ASR performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionTransfer LearningSimilar Papers 제목 키워드 기반
An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS
Zero-shot multi-speaker text-to-speech (TTS) systems rely on speaker embeddings to synthesize speech in the voice of an unseen speaker, using only a short reference utterance. While many speaker embeddings have been deve…
Speaker Recognitiontext-to-speechText to SpeechZero-Shot Multi-Speaker TTSU-vectors: Generating clusterable speaker embedding from unlabeled data
Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second…
Domain AdaptationSpeaker RecognitionRecursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
This paper proposes a method for extracting speaker embedding for each speaker from a variable-length recording containing multiple speakers. Speaker embeddings are crucial not only for speaker recognition but also for v…
speaker-diarizationSpeaker DiarizationSpeaker RecognitionSpeaker VerificationContent-Aware Speaker Embeddings for Speaker Diarisation
Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware sp…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)ClusteringSpeaker Recognition+3Revealing Emotional Clusters in Speaker Embeddings: A Contrastive Learning Strategy for Speech Emotion Recognition
Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assume…
Contrastive LearningEmotion RecognitionSpeech Emotion Recognition