Search Results for author:
Found 9 papers, 6 papers with code
Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches
Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition and query-by-example search.
Visually grounded learning of keyword prediction from untranscribed speech
In this setting of images paired with untranscribed spoken captions, we consider whether computer vision systems can be used to obtain textual labels for the speech.
Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings
Query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments.
Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multilingual Jointly Trained Acoustic and Written Word Embeddings
The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages.
Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings
We find that word error rate can be reduced by a large margin by pre-training the acoustic segment representation with AWEs, and additional (smaller) gains can be obtained by pre-training the word prediction layer with AGWEs.
Acoustic span embeddings for multilingual query-by-example search
In this work, we generalize AWE training to spans of words, producing acoustic span embeddings (ASE), and explore the application of ASE to QbE with arbitrary-length queries in multiple unseen languages.
What Do Self-Supervised Speech Models Know About Words?
Many self-supervised speech models (S3Ms) have been introduced over the last few years, improving performance and data efficiency on various speech tasks.
Neural approaches to spoken content embedding
As an alternative, acoustic word embeddings -- fixed-dimensional vector representations of variable-length spoken word segments -- have begun to be considered for such tasks as well.
