Unsupervised word discovery from speech using automatic segmentation into syllable-like units

By Okko Johannes Räsänen, Gabriel Doyle, Michael C. Frank. 2015

83 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, Experimental and Cognitive Psychology, Natural Language Processing, Speech & Audio

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Developmental and Educational Psychology

In Experimental and Cognitive Psychology

In Natural Language Processing

In Speech & Audio

Citations in the corpus

Unsupervised Speech Recognition (2021, methodology): “There has been a lot of prior work in unsupervised speech segmentation (Kamper et al., 2017a,b; Rasanen et al., 2015; Kreuk et al., 2020) but here we simply use a method based on clustering the wav2vec 2.0 speech representations c1, . . . , cT .”
A segmental framework for fully-unsupervised large-vocabulary speech recognition (2016, methodology): “To our knowledge, this is the ﬁrst full-coverage unsupervised speech recognition system to report results in this regime; previous systems have either focused on identifying isolated terms [1,18,19], were speaker-dependent [22,23], or used only a small vocabulary [21,24].”
The Zero Resource Speech Challenge 2015: Proposed Approaches and Results (2016, methodology): “[8] proposes to start spoken term discovery based on the segmentation of the input signal into syllables.”
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces (2018, methodology): “The third one is the recurring syllable-unit segmenter called SylSeg [37], a fast and heuristic method that applies unsupervised syllable segmentation and clustering, to predict recurring syllable sequences as words.”
An embedded segmental K-means model for unsupervised segmentation and clustering of speech (2017, background): “In a similar way it can be shown that the Gibbs sampling equations for segmentation and component assignments for BES-GMM (as given in [20]) approach (3) and (5), respectively, in the limit σ2 → 0, when all other hyperparameters are fixed.”
Virtual Phone Discovery for Speech Synthesis Without Text (2019, unknown): “3 Osc [32] 75.”
Unsupervised Word Segmentation and Lexicon Discovery Using Acoustic Word Embeddings (2016, methodology): “Many of the previous studies [11], [12], [23], [44] use a ﬁrst-pass method to ﬁnd positions of high acoustic change and then only allow word boundaries at these positions.”
Measuring the perceptual availability of phonological features during language acquisition using unsupervised binary stochastic autoencoders (2019, background): “Participating systems (Badino et al., 2015; Renshaw et al., 2015; Agenbag and Niesler, 2015; Chen et al., 2015; Baljekar et al., 2015; Räsänen et al., 2015; Lyzinski et al., 2015; Zeghidour et al., 2016; Heck et al., 2016; Srivastava and Shrivastava, 2016; Kamper et al., 2017b; Chen et al., 2017;…”