Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery
Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature vectors are more similar within a segment than across the segments. Therefore, for strong segmentation performance, it is crucial that the features represent the phonetic properties of a frame more than other factors of variability. We achieve this via a self-expressing autoencoder framework. It consists of a single encoder and two decoders with shared weights. The encoder projects the input features into a latent representation. One of the decoders tries to reconstruct the input from these latent representations and the other from the self-expressed version of them. We use the obtained features to segment and cluster the speech data. We evaluate the performance of the proposed method in the Zero Resource 2020 challenge unit discovery task. The proposed system consistently outperforms the baseline, demonstrating the usefulness of the method in learning representations.
Code (0)
등록된 구현이 없습니다.
Tasks
SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences
Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Constituency ParsingInductive Bias+2Bridging Speech and Textual Pre-trained Models with Unsupervised ASR
Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Question Answeringspeech-recognition+2Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge
Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as…
Acoustic Unit DiscoveryLanguage ModelingLanguage ModellingResynthesisUnsupervised Spoken Term Detection with Spoken Queries by Multi-level Acoustic Patterns with Varying Model Granularity
This paper presents a new approach for unsupervised Spoken Term Detection with spoken queries using multiple sets of acoustic patterns automatically discovered from the target corpus. The different pattern HMM configurat…
Introducing Semantics into Speech Encoders
Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM)…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Entity Resolutionintent-classification+10