H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Speaker IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Ordered and Binary Speaker Embedding
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 RecognitionSerialized Multi-Layer Multi-Head Attention for Neural Speaker Embedding
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 VerificationS-vectors and TESA: Speaker Embeddings and a Speaker Authenticator Based on Transformer Encoder
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 VerificationEffective Incorporation of Speaker Information in Utterance Encoding in Dialog
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 GenerationSelf-supervised speaker embeddings
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