Picture for Corey Miller

Corey Miller

Style-agnostic evaluation of ASR using multiple reference transcripts

Add code
Dec 10, 2024
Viaarxiv icon

Reverb: Open-Source ASR and Diarization from Rev

Add code
Oct 04, 2024
Viaarxiv icon

Quantification of stylistic differences in human- and ASR-produced transcripts of African American English

Add code
Sep 04, 2024
Figure 1 for Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
Figure 2 for Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
Figure 3 for Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
Figure 4 for Quantification of stylistic differences in human- and ASR-produced transcripts of African American English
Viaarxiv icon

Updated Corpora and Benchmarks for Long-Form Speech Recognition

Add code
Sep 26, 2023
Figure 1 for Updated Corpora and Benchmarks for Long-Form Speech Recognition
Figure 2 for Updated Corpora and Benchmarks for Long-Form Speech Recognition
Figure 3 for Updated Corpora and Benchmarks for Long-Form Speech Recognition
Figure 4 for Updated Corpora and Benchmarks for Long-Form Speech Recognition
Viaarxiv icon

Earnings-22: A Practical Benchmark for Accents in the Wild

Add code
Mar 29, 2022
Figure 1 for Earnings-22: A Practical Benchmark for Accents in the Wild
Figure 2 for Earnings-22: A Practical Benchmark for Accents in the Wild
Figure 3 for Earnings-22: A Practical Benchmark for Accents in the Wild
Figure 4 for Earnings-22: A Practical Benchmark for Accents in the Wild
Viaarxiv icon

A High Quality Text-To-Speech System Composed of Multiple Neural Networks

Add code
Dec 05, 1998
Figure 1 for A High Quality Text-To-Speech System Composed of Multiple Neural Networks
Viaarxiv icon

Variation and Synthetic Speech

Add code
Nov 17, 1997
Viaarxiv icon