Publications (11)
Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches
Shane Settle, Karen Livescu
Acoustic word embeddings --- fixed-dimensional vector representations of variable-length spoken word segments --- have begun to be considered for tasks such as speech recognition a…
Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings
Shane Settle, Keith Levin, Herman Kamper +1
Query-by-example search often uses dynamic time warping (DTW) for comparing queries and proposed matching segments. Recent work has shown that comparing speech segments by represen…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Neural approaches to spoken content embedding
Shane Settle
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…
Acoustic span embeddings for multilingual query-by-example search
Yushi Hu, Shane Settle, Karen Livescu
Query-by-example (QbE) speech search is the task of matching spoken queries to utterances within a search collection. In low- or zero-resource settings, QbE search is often address…
Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition
Shane Settle, Kartik Audhkhasi, Karen Livescu +1
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. However, A2W syst…