2017/11/05 by Yu-An Chung, James Glass, Chung, Yu-An +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Natural Language Processing Techniques #Speech Recognition and Synthesis
paper · pdf · doi:10.48550/arxiv.1711.01515
openalex publication_date 2017/11/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the segments, and are close to other vectors in the embedding space if their corresponding segments are semantically similar. The design of the proposed model is based on the RNN Encoder-Decoder framework, and borrows the methodology of continuous skip-grams for training. The learned vector representations are evaluated on 13 widely used word similarity benchmarks, and achieved competitive results to that of GloVe. The biggest advantage of the proposed model is its capability of extracting semantic information of audio segments taken directly from raw speech, without relying on any other modalities such as text or images, which are challenging and expensive to collect and annotate.