paper-with-me

Papers

H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model

2019-10-17 · Yanpei Shi, Qiang Huang, Thomas Hain

In this paper, a hierarchical attention network to generate utterance-level embeddings (H-vectors) for speaker identification is proposed. Since different parts of an utterance may have different contributions to speaker identities, the use of hierarchical structure aims to learn speaker related information locally and globally. In the proposed approach, frame-level encoder and attention are applied on segments of an input utterance and generate individual segment vectors. Then, segment level attention is applied on the segment vectors to construct an utterance representation. To evaluate the effectiveness of the proposed approach, NIST SRE 2008 Part1 dataset is used for training, and two datasets, Switchboard Cellular part1 and CallHome American English Speech, are used to evaluate the quality of extracted utterance embeddings on speaker identification and verification tasks. In comparison with two baselines, X-vector, X-vector+Attention, the obtained results show that H-vectors can achieve a significantly better performance. Furthermore, the extracted utterance-level embeddings are more discriminative than the two baselines when mapped into a 2D space using t-SNE.

📄 PDF Abstract BibTeX arXiv:1910.07900

Code (0)

등록된 구현이 없습니다.

Tasks

Speaker Identification

Methods 이 논문이 사용한 방법론

American 설명 없음

Similar Papers 제목 키워드 기반

Ordered and Binary Speaker Embedding

2023-05-25 · Jiaying Wang, Xianglong Wang, Namin Wang, Lantian Li 외

Modern speaker recognition systems represent utterances by embedding vectors. Conventional embedding vectors are dense and non-structural. In this paper, we propose an ordered binary embedding approach that sorts the dim…

ClusteringRetrievalSpeaker IdentificationSpeaker Recognition

Serialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding

2021-07-14 · Hongning Zhu, Kong Aik Lee, Haizhou Li

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 utter…

Speaker VerificationText-Independent Speaker Verification

S-vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder

2020-08-11 · N J Metilda Sagaya Mary, S Umesh, Sandesh V Katta

One of the most popular speaker embeddings is x-vectors, which are obtained from an architecture that gradually builds a larger temporal context with layers. In this paper, we propose to derive speaker embeddings from Tr…

SentenceSpeaker Verification

Effective Incorporation of Speaker Information in Utterance Encoding in Dialog

2019-07-12 · Tianyu Zhao, Tatsuya Kawahara

In dialog studies, we often encode a dialog using a hierarchical encoder where each utterance is converted into an utterance vector, and then a sequence of utterance vectors is converted into a dialog vector. Since knowi…

Response Generation

Self-supervised speaker embeddings

2019-04-06 · Themos Stafylakis, Johan Rohdin, Oldrich Plchot, Petr Mizera 외

Contrary to i-vectors, speaker embeddings such as x-vectors are incapable of leveraging unlabelled utterances, due to the classification loss over training speakers. In this paper, we explore an alternative training stra…

DecoderGeneral Classification