paper-with-me

홈 › Papers

Deep convolutional acoustic word embeddings using word-pair side information

2015-10-05 · Herman Kamper, Weiran Wang, Karen Livescu

Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech segment to a vector in a fixed-dimensional space; the resulting acoustic word embeddings need to allow for accurate discrimination between different word types, directly in the embedding space. We compare several old and new approaches in a word discrimination task. Our best approach uses side information in the form of known word pairs to train a Siamese convolutional neural network (CNN): a pair of tied networks that take two speech segments as input and produce their embeddings, trained with a hinge loss that separates same-word pairs and different-word pairs by some margin. A word classifier CNN performs similarly, but requires much stronger supervision. Both types of CNNs yield large improvements over the best previously published results on the word discrimination task.

📄 PDF Abstract BibTeX arXiv:1510.01032

Code (1)

kamperh/recipe_swbd_wordembeds 공식 구현

Tasks

speech-recognitionSpeech RecognitionWord Embeddings

Similar Papers 제목 키워드 기반

Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search

2018-06-10 · Yougen Yuan, Cheung-Chi Leung, Lei Xie, Hongjie Chen 외

We propose to learn acoustic word embeddings with temporal context for query-by-example (QbE) speech search. The temporal context includes the leading and trailing word sequences of a word. We assume that there exist spo…

Dynamic Time WarpingTripletWord Embeddings

Neural approaches to spoken content embedding

2023-08-28 · Shane Settle

Comparing spoken segments is a central operation to speech processing. Traditional approaches in this area have favored frame-level dynamic programming algorithms, such as dynamic time warping, because they require no su…

Automatic Speech RecognitionDynamic Time Warpingspeech-recognitionSpeech Recognition+1

Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches

2016-11-08 · Shane Settle, Karen Livescu

Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search. Such embeddi…

Dynamic Time WarpingGeneral Classificationspeech-recognitionSpeech Recognition+1

Asymmetric Proxy Loss for Multi-View Acoustic Word Embeddings

2022-03-30 · Myunghun Jung, Hoirin Kim

Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words. With multi-view learning, where text labels are considere…

Metric LearningMULTI-VIEW LEARNINGTripletWord Embeddings

Multi-view Recurrent Neural Acoustic Word Embeddings

2016-11-14 · Wanjia He, Weiran Wang, Karen Livescu

Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval an…

RetrievalWord EmbeddingsWord Similarity