Related papers: Unsupervised Word Segmentation from Discrete Speec…
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection…
Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with…
Spoken Language Understanding (SLU) is a task that aims to extract semantic information from spoken utterances. Previous research has made progress in end-to-end SLU by using paired speech-text data, such as pre-trained Automatic Speech…
Subwords have become the standard units of text in NLP, enabling efficient open-vocabulary models. With algorithms like byte-pair encoding (BPE), subword segmentation is viewed as a preprocessing step applied to the corpus before training.…
Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited…
Recent work in spoken language modeling shows the possibility of learning a language unsupervisedly from raw audio without any text labels. The approach relies first on transforming the audio into a sequence of discrete units (or…
Most speech and language technologies are trained with massive amounts of speech and text information. However, most of the world languages do not have such resources or stable orthography. Systems constructed under these almost zero…
Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…
This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative…
In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on…
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 supervision, but they…
In this paper, we investigated a speech augmentation based unsupervised learning approach for keyword spotting (KWS) task. KWS is a useful speech application, yet also heavily depends on the labeled data. We designed a CNN-Attention…
This paper presents a model-based, unsupervised algorithm for recovering word boundaries in a natural-language text from which they have been deleted. The algorithm is derived from a probability model of the source that generated the text.…
Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the…
In reverberant conditions with multiple concurrent speakers, each microphone acquires a mixture signal of multiple speakers at a different location. In over-determined conditions where the microphones out-number speakers, we can narrow down…
We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation.…
Neural text-to-speech (TTS) models can synthesize natural human speech when trained on large amounts of transcribed speech. However, collecting such large-scale transcribed data is expensive. This paper proposes an unsupervised pre-training…
Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early term discovery systems focused on identifying…
Word segmentation is a low-level NLP task that is non-trivial for a considerable number of languages. In this paper, we present a sequence tagging framework and apply it to word segmentation for a wide range of languages with different…
Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…