Investigation of Speaker Representation for Target-Speaker Speech Processing

• URL: http://arxiv.org/abs/2410.11243v1
• Date: Tue, 15 Oct 2024 03:58:13 GMT
• Title: Investigation of Speaker Representation for Target-Speaker Speech Processing
• Authors: Takanori Ashihara, Takafumi Moriya, Shota Horiguchi, Junyi Peng, Tsubasa Ochiai, Marc Delcroix, Kohei Matsuura, Hiroshi Sato,
• Abstract summary: This paper aims to address a fundamental question: what is the preferred speaker embedding for target-speaker speech processing tasks? For the TS-ASR, TSE, and p-VAD tasks, we compare pre-trained speaker encoders that compute speaker embeddings from pre-recorded enrollment speech of the target speaker with ideal speaker embeddings derived directly from the target speaker's identity in the form of a one-hot vector. Our analysis reveals speaker verification performance is somewhat unrelated to TS task performances, the one-hot vector outperforms enrollment-based ones, and the optimal embedding depends on the input mixture.
• Score: 49.110228525976794
• License:
• Abstract: Target-speaker speech processing (TS) tasks, such as target-speaker automatic speech recognition (TS-ASR), target speech extraction (TSE), and personal voice activity detection (p-VAD), are important for extracting information about a desired speaker's speech even when it is corrupted by interfering speakers. While most studies have focused on training schemes or system architectures for each specific task, the auxiliary network for embedding target-speaker cues has not been investigated comprehensively in a unified cross-task evaluation. Therefore, this paper aims to address a fundamental question: what is the preferred speaker embedding for TS tasks? To this end, for the TS-ASR, TSE, and p-VAD tasks, we compare pre-trained speaker encoders (i.e., self-supervised or speaker recognition models) that compute speaker embeddings from pre-recorded enrollment speech of the target speaker with ideal speaker embeddings derived directly from the target speaker's identity in the form of a one-hot vector. To further understand the properties of ideal speaker embedding, we optimize it using a gradient-based approach to improve performance on the TS task. Our analysis reveals that speaker verification performance is somewhat unrelated to TS task performances, the one-hot vector outperforms enrollment-based ones, and the optimal embedding depends on the input mixture.

Related papers

• Self supervised learning for robust voice cloning [3.7989740031754806]
  We use features learned in a self-supervised framework to produce high quality speech representations. The learned features are used as pre-trained utterance-level embeddings and as inputs to a Non-Attentive Tacotron based architecture. This method enables us to train our model in an unlabeled multispeaker dataset as well as use unseen speaker embeddings to copy a speaker's voice.
  arXiv  Detail & Related papers  (2022-04-07T13:05:24Z)
• Improved Relation Networks for End-to-End Speaker Verification and Identification [0.0]
  Speaker identification systems are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples. We propose improved relation networks for speaker verification and few-shot (unseen) speaker identification. Inspired by the use of prototypical networks in speaker verification, we train the model to classify samples in the current episode amongst all speakers present in the training set.
  arXiv  Detail & Related papers  (2022-03-31T17:44:04Z)
• Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings [53.11450530896623]
  This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize "who spoke what" Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion. The proposed model achieves substantially better accuracy than a prior streaming model and shows comparable or sometimes even superior results to the state-of-the-art offline SA-ASR model.
  arXiv  Detail & Related papers  (2022-03-30T21:42:00Z)
• PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction [90.55375210094995]
  Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. We propose an end-to-end deep learning framework, dubbed PL-EESR, for robust speaker representation extraction.
  arXiv  Detail & Related papers  (2021-10-03T07:05:29Z)
• Content-Aware Speaker Embeddings for Speaker Diarisation [3.6398652091809987]
  The content-aware speaker embeddings (CASE) approach is proposed. Case factorises automatic speech recognition (ASR) from speaker recognition to focus on modelling speaker characteristics. Case achieved a 17.8% relative speaker error rate reduction over conventional methods.
  arXiv  Detail & Related papers  (2021-02-12T12:02:03Z)
• Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers [38.3469744871394]
  We propose an end-to-end speaker-attributed automatic speech recognition model. It unifies speaker counting, speech recognition, and speaker identification on overlapped speech.
  arXiv  Detail & Related papers  (2020-06-19T02:05:18Z)
• Active Speakers in Context [88.22935329360618]
  Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. This paper introduces the Active Speaker Context, a novel representation that models relationships between multiple speakers over long time horizons. Our experiments show that a structured feature ensemble already benefits the active speaker detection performance.
  arXiv  Detail & Related papers  (2020-05-20T01:14:23Z)
• Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention [70.82604384963679]
  This paper investigates a self-adaptation method for speech enhancement using auxiliary speaker-aware features. We extract a speaker representation used for adaptation directly from the test utterance.
  arXiv  Detail & Related papers  (2020-02-14T05:05:36Z)
• Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam [100.95498268200777]
  SpeakerBeam exploits an adaptation utterance of the target speaker to extract his/her voice characteristics. SpeakerBeam sometimes fails when speakers have similar voice characteristics, such as in same-gender mixtures. We show experimentally that these strategies greatly improve speech extraction performance, especially for same-gender mixtures.
  arXiv  Detail & Related papers  (2020-01-23T05:36:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.