Temporal properties of spontaneous speech—a syllable-centric perspective von Greenberg, Steven, Carvey, Hannah, Hitchcock, Leah, Chang, Shuangyu

Volltext

End-to-end speech recognition accuracy metric for voice-search tasks von Levit, M., Shuangyu Chang, Buntschuh, B., Kibre, N.

Volltext

An elitist approach to automatic articulatory-acoustic feature classification for phonetic characterization of spoken language von Chang, Shuangyu, Wester, Mirjam, Greenberg, Steven

Volltext

Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition von Behre, Piyush, Tan, Sharman, Varadharajan, Padma, Chang, Shuangyu

Volltext

Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition von Tan, Sharman, Behre, Piyush, Kibre, Nick, Alphonso, Issac, Chang, Shuangyu

Volltext bestellen

Streaming Punctuation for Long-form Dictation with Transformers von Behre, Piyush, Tan, Sharman, Varadharajan, Padma, Chang, Shuangyu

Volltext bestellen

Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages von Miao, Li, Wu, Jian, Behre, Piyush, Chang, Shuangyu, Parthasarathy, Sarangarajan

Volltext bestellen

External Language Model Integration for Factorized Neural Transducers von Levit, Michael, Parthasarathy, Sarangarajan, Aksoylar, Cem, Rasooli, Mohammad Sadegh, Chang, Shuangyu

Volltext bestellen

Garbage modeling with decoys for a sequential recognition scenario von Levit, M., Shuangyu Chang, Buntschuh, B.

Volltext bestellen

TRScore: A Novel GPT-based Readability Scorer for ASR Segmentation and Punctuation model evaluation and selection von Behre, Piyush, Tan, Sharman, Shah, Amy, Kesavamoorthy, Harini, Chang, Shuangyu, Zuo, Fei, Basoglu, Chris, Pathak, Sayan

Volltext bestellen

LSTM-LM with Long-Term History for First-Pass Decoding in Conversational Speech Recognition von Chen, Xie, Parthasarathy, Sarangarajan, Gale, William, Chang, Shuangyu, Zeng, Michael

Volltext bestellen

Smart Speech Segmentation using Acousto-Linguistic Features with look-ahead von Behre, Piyush, Parihar, Naveen, Tan, Sharman, Shah, Amy, Sharma, Eva, Liu, Geoffrey, Chang, Shuangyu, Khalil, Hosam, Basoglu, Chris, Pathak, Sayan

Volltext bestellen

Long-span language modeling for speech recognition von Parthasarathy, Sarangarajan, Gale, William, Chen, Xie, Polovets, George, Chang, Shuangyu

Volltext bestellen

EYES-OFF TRAINING FOR AUTOMATIC SPEECH RECOGNITION von CHANG, Shuangyu, MALHOTRA, Hemant, FATEHPURIA, Pradip Kumar

Volltext bestellen

Scalable entities and patterns mining pipeline to improve automatic speech recognition von Alphonso, Issac John, Anastasakos, Anastasios, Gupta, Ankur, Mehta, Rupeshkumar Rasiklal, Guha, Satarupa, Chang, Shuangyu

Volltext bestellen

Streaming Punctuation for Long-form Dictation with Transformers von Behre, Piyush, Tan, Sharman, Varadharajan, Padma, Chang, Shuangyu

Volltext

Four-in-One: A Joint Approach to Inverse Text Normalization, Punctuation, Capitalization, and Disfluency for Automatic Speech Recognition von Tan, Sharman, Behre, Piyush, Kibre, Nick, Issac Alphonso, Chang, Shuangyu

Volltext

Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages von Li, Miao, Wu, Jian, Behre, Piyush, Chang, Shuangyu, Parthasarathy, Sarangarajan

Volltext

Microsegment secure speech transcription von Huang, Xuedong, Li, Dong, Malhotra, Hemant, Jiang, Li, Garcia Dos Santos, Ivo Jose, Chang, Shuangyu

Volltext bestellen

SCALABLE ENTITIES AND PATTERNS MINING PIPELINE TO IMPROVE AUTOMATIC SPEECH RECOGNITION von ALPHONSO, Issac John, CHANG, Shuangyu, GUPTA, Ankur, MEHTA, Rupeshkumar Rasiklal, ANASTASAKOS, Anastasios, GUHA, Satarupa

Volltext bestellen