Spoken Word2Vec: Learning Skipgram Embeddings from Speech
Text word embeddings that encode distributional semantics work by modeling contextual similarities of frequently occurring words. Acoustic word embeddings, on the other hand, typically encode low-level phonetic similarities. Semantic embeddings for spoken words have been previously explored using analogous algorithms to Word2Vec, but the resulting vectors still mainly encoded phonetic rather than semantic features. In this paper, we examine the assumptions and architectures used in previous works and show experimentally how shallow skipgram-like algorithms fail to encode distributional semantics when the input units are acoustically correlated. We illustrate the potential of an alternative deep end-to-end variant of the model and examine the effects on the resulting embeddings, showing positive results of semantic relatedness in the embedding space.
Code (1)
Tasks
ClusteringWord EmbeddingsSimilar Papers 제목 키워드 기반
Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic informat…
DecoderLearning Word EmbeddingsWord EmbeddingsWord SimilarityNon-Linear Relational Information Probing in Word Embeddings
Pre-trained word embeddings such as SkipGram and GloVe are known to contain a myriad of useful information about words. In this work, we use multilayer perceptrons (MLP) to probe the relational information contained in t…
RelationWord EmbeddingsQuerying Word Embeddings for Similarity and Relatedness
Word embeddings obtained from neural network models such as Word2Vec Skipgram have become popular representations of word meaning and have been evaluated on a variety of word similarity and relatedness norming data. Skip…
Word EmbeddingsWord SimilarityAlmost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the lan…
speech-recognitionSpeech RecognitionUnsupervised Speech RecognitionLeveraging multilingual transfer for unsupervised semantic acoustic word embeddings
Acoustic word embeddings (AWEs) are fixed-dimensional vector representations of speech segments that encode phonetic content so that different realisations of the same word have similar embeddings. In this paper we explo…
Word EmbeddingsWord Similarity