Picture for Zelin Wu

Zelin Wu

Text Injection for Neural Contextual Biasing

Jun 05, 2024
Viaarxiv icon

Deferred NAM: Low-latency Top-K Context Injection via DeferredContext Encoding for Non-Streaming ASR

Apr 15, 2024
Viaarxiv icon

High-precision Voice Search Query Correction via Retrievable Speech-text Embedings

Jan 08, 2024
Viaarxiv icon

SLM: Bridge the thin gap between speech and text foundation models

Sep 30, 2023
Figure 1 for SLM: Bridge the thin gap between speech and text foundation models
Figure 2 for SLM: Bridge the thin gap between speech and text foundation models
Figure 3 for SLM: Bridge the thin gap between speech and text foundation models
Figure 4 for SLM: Bridge the thin gap between speech and text foundation models
Viaarxiv icon

Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm

Sep 29, 2023
Viaarxiv icon

A Deliberation-based Joint Acoustic and Text Decoder

Mar 23, 2023
Figure 1 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 2 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 3 for A Deliberation-based Joint Acoustic and Text Decoder
Figure 4 for A Deliberation-based Joint Acoustic and Text Decoder
Viaarxiv icon

Streaming Intended Query Detection using E2E Modeling for Continued Conversation

Aug 29, 2022
Figure 1 for Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Figure 2 for Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Figure 3 for Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Figure 4 for Streaming Intended Query Detection using E2E Modeling for Continued Conversation
Viaarxiv icon

Speech Recognition with Augmented Synthesized Speech

Sep 25, 2019
Figure 1 for Speech Recognition with Augmented Synthesized Speech
Figure 2 for Speech Recognition with Augmented Synthesized Speech
Figure 3 for Speech Recognition with Augmented Synthesized Speech
Figure 4 for Speech Recognition with Augmented Synthesized Speech
Viaarxiv icon

Improving Performance of End-to-End ASR on Numeric Sequences

Jul 01, 2019
Figure 1 for Improving Performance of End-to-End ASR on Numeric Sequences
Figure 2 for Improving Performance of End-to-End ASR on Numeric Sequences
Figure 3 for Improving Performance of End-to-End ASR on Numeric Sequences
Viaarxiv icon

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Add code
Feb 21, 2019
Figure 1 for Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Figure 2 for Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Figure 3 for Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Viaarxiv icon