Using Pronunciation-Based Morphological Subword Units to Improve OOV Handling in Keyword Search von Yanzhang He, Baumann, Peter, Hao Fang, Hutchinson, Brian, Jaech, Aaron, Ostendorf, Mari, Fosler-Lussier, Eric, Pierrehumbert, Janet

Volltext

Self-adaptive Failure Detector for Peer-to-Peer Distributed System Considering the Link Faults von He, Yanzhang, Jiang, Xiaohong, Dai, Changbo, Fan, Zikun

Volltext

RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models von Qiu, David, Rim, David, Ding, Shaojin, Rybakov, Oleg, He, Yanzhang

Volltext bestellen

Closing the Gap between Single-User and Multi-User VoiceFilter-Lite von Rikhye, Rajeev, Wang, Quan, Liang, Qiao, He, Yanzhang, McGraw, Ian

Volltext bestellen

2-bit Conformer quantization for automatic speech recognition von Rybakov, Oleg, Meadowlark, Phoenix, Ding, Shaojin, Qiu, David, Li, Jian, Rim, David, He, Yanzhang

Volltext bestellen

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems von Bijwadia, Shaan, Chang, Shuo-yiin, Li, Bo, Sainath, Tara, Zhang, Chao, He, Yanzhang

Volltext

Turn-Taking Prediction for Natural Conversational Speech von Chang, Shuo-yiin, Li, Bo, Sainath, Tara N, Zhang, Chao, Strohman, Trevor, Liang, Qiao, He, Yanzhang

Volltext bestellen

Improving Deliberation by Text-Only and Semi-Supervised Training von Hu, Ke, Sainath, Tara N, He, Yanzhang, Prabhavalkar, Rohit, Strohman, Trevor, Mavandadi, Sepand, Wang, Weiran

Volltext bestellen

Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models von Prabhavalkar, Rohit, Meng, Zhong, Wang, Weiran, Stooke, Adam, Cai, Xingyu, He, Yanzhang, Narayanan, Arun, Hwang, Dongseong, Sainath, Tara N, Moreno, Pedro J

Volltext bestellen

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models von Hernandez, Steven M, Zhao, Ding, Ding, Shaojin, Bruguier, Antoine, Prabhavalkar, Rohit, Sainath, Tara N, He, Yanzhang, McGraw, Ian

Volltext bestellen

Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition von Ding, Shaojin, Rikhye, Rajeev, Liang, Qiao, He, Yanzhang, Wang, Quan, Narayanan, Arun, O'Malley, Tom, McGraw, Ian

Volltext bestellen

USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models von Ding, Shaojin, Qiu, David, Rim, David, He, Yanzhang, Rybakov, Oleg, Li, Bo, Prabhavalkar, Rohit, Wang, Weiran, Sainath, Tara N, Han, Zhonglin, Li, Jian, Yazdanbakhsh, Amir, Agrawal, Shivani

Volltext bestellen

Cross-attention conformer for context modeling in speech enhancement for ASR von Narayanan, Arun, Chiu, Chung-Cheng, O'Malley, Tom, Wang, Quan, He, Yanzhang

Volltext bestellen

Personalized Keyphrase Detection using Speaker and Environment Information von Rikhye, Rajeev, Wang, Quan, Liang, Qiao, He, Yanzhang, Zhao, Ding, Yiteng, Huang, Narayanan, Arun, McGraw, Ian

Volltext bestellen

RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models von Qiu, David, Rim, David, Ding, Shaojin, Rybakov, Oleg, He, Yanzhang

Volltext

Massive End-to-end Models for Short Search Queries von Wang, Weiran, Prabhavalkar, Rohit, Hwang, Dongseong, Li, Qiujia, Sim, Khe Chai, Li, Bo, Qin, James, Cai, Xingyu, Stooke, Adam, Meng, Zhong, Zheng, CJ, He, Yanzhang, Sainath, Tara, Mengibar, Pedro Moreno

Volltext bestellen

HPACS: A High Privacy and Availability Cloud Storage Platform with Matrix Encryption von He, Yanzhang, Jiang, Xiaohong, Ye, Kejiang, Ma, Ran, Li, Xiang

Volltext

Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging von Prabhavalkar, Rohit, He, Yanzhang, Rybach, David, Campbell, Sean, Narayanan, Arun, Strohman, Trevor, Sainath, Tara N

Volltext bestellen

A Language Agnostic Multilingual Streaming On-Device ASR System von Li, Bo, Sainath, Tara N, Pang, Ruoming, Chang, Shuo-yiin, Xu, Qiumin, Strohman, Trevor, Chen, Vince, Liang, Qiao, Liu, Heguang, He, Yanzhang, Haghani, Parisa, Bidichandani, Sameer

Volltext bestellen

Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition von Li, Wei, Qin, James, Chiu, Chung-Cheng, Pang, Ruoming, He, Yanzhang

Volltext bestellen