Word-level Acoustic Modeling with Convolutional Vector Regression

By Andrew L. Maas, Stephen D. Miller, Tyler M. O'Neil, Andrew Y. Ng, Patrick Nguyen. 2012

How researchers see this paper

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

Citations in the corpus

Order Matters: Sequence to sequence for sets (2015, neutral): “For example, the chain rule is used to decompose the joint probability of sequences of words, and can be implemented by an LSTM without making any conditional independence assumption.”
Acoustically Grounded Word Embeddings for Improved Acoustics-to-word Speech Recognition (2019, background): “Early work on learning acoustic word embeddings [20, 27] used word-level acoustic representations precisely for rescoring in large-vocabulary speech recognition systems.”
Self-Supervised Speech Representation Learning: A Review (2022, background): “For example, searching within a corpus of recorded speech for segments that match a given (written or spoken) query can be seen as finding segments whose representations are most similar to that of the query [118], [192], [193], [194]; word embeddings can be defined by pooling representations of ins”
Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings (2013, background): “These include downsampling [13, 14, 15, 16], phonetic acoustic model-derived features [17, 18], and convolutional deep neural networks [19].”
Deep convolutional acoustic word embeddings using word-pair side information (2015, methodology): “[6] trained a regression CNN that reconstructs a semantic word embedding from acoustic speech input; these features were used in a segmental conditional random field ASR system.”
Learning Word Embeddings: Unsupervised Methods for Fixed-size Representations of Variable-length Speech Segments (2018, methodology): “DNNs have been used to derive embeddings by training them with a supervised objective, although not for speech recognition per se: [20, 21] alternate convolutional and pooling layers, finishing with a fixed length vector.”
Semantic Query-by-example Speech Search Using Visual Grounding (2019, methodology): “Various acoustic embedding functions have been proposed, with neural models used in several studies [16, 18, 23–30].”
Discriminative acoustic word embeddings: Tecurrent neural network-based approaches (2016, methodology): “Therehas been some, thus far limited, work on acoustic word embeddings, focused on a number of embedding models, training approaches, and tasks [10, 11, 12, 13, 14, 15, 16, 17].”