Michael Alan Picheny

Michael Alan Picheny

New York University

H-index: 64

North America-United States

About Michael Alan Picheny

Michael Alan Picheny, With an exceptional h-index of 64 and a recent h-index of 33 (since 2020), a distinguished researcher at New York University, specializes in the field of Speech Recognition, Speech Synthesis, Deep Learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Multilingual intent recognition

Dual learning for large vocabulary on-device ASR

Improving joint speech-text representations without alignment

Twenty-Five Years of Evolution in Speech and Language Processing

A comparison of semi-supervised learning techniques for streaming asr at scale

Leveraging unpaired text data for training end-to-end spoken language understanding systems

Towards disentangled speech representations

Towards measuring fairness in speech recognition: Casual conversations dataset transcriptions

Michael Alan Picheny Information

University

Position

- Courant CS and CDS

Citations(all)

15756

Citations(since 2020)

4542

Cited By

13623

hIndex(all)

64

hIndex(since 2020)

33

i10Index(all)

173

i10Index(since 2020)

75

Email

University Profile Page

Google Scholar

Michael Alan Picheny Skills & Research Interests

Speech Recognition

Speech Synthesis

Deep Learning

Top articles of Michael Alan Picheny

Title

Journal

Author(s)

Publication Date

Multilingual intent recognition

2024/2/13

Dual learning for large vocabulary on-device ASR

Cal Peyser

Ronny Huang

Tara Sainath

Rohit Prabhavalkar

Michael Picheny

...

2023/1/9

Improving joint speech-text representations without alignment

arXiv preprint arXiv:2308.06125

Cal Peyser

Zhong Meng

Ke Hu

Rohit Prabhavalkar

Andrew Rosenberg

...

2023/8/11

Twenty-Five Years of Evolution in Speech and Language Processing

IEEE Signal Processing Magazine

Dong Yu

Yifan Gong

Michael Alan Picheny

Bhuvana Ramabhadran

Dilek Hakkani-Tür

...

2023/7/20

A comparison of semi-supervised learning techniques for streaming asr at scale

Cal Peyser

Michael Picheny

Kyunghyun Cho

Rohit Prabhavalkar

W Ronny Huang

...

2023/6/4

Leveraging unpaired text data for training end-to-end spoken language understanding systems

2023/2/21

Towards disentangled speech representations

arXiv preprint arXiv:2208.13191

Cal Peyser

Ronny Huang Andrew Rosenberg Tara N Sainath

Michael Picheny

Kyunghyun Cho

2022/8/28

Towards measuring fairness in speech recognition: Casual conversations dataset transcriptions

Chunxi Liu

Michael Picheny

Leda Sarı

Pooja Chitkara

Alex Xiao

...

2022/5/23

Using closed captions as parallel training data for customization of closed captioning systems

2022/2/15

Multimodal clustering networks for self-supervised learning from unlabeled videos

Brian Chen

Andrew Rouditchenko

Kevin Duarte

Hilde Kuehne

Samuel Thomas

...

2021

Detecting and recovering out-of-vocabulary words in voice-to-text transcription systems

2021/11/23

Optimizing speech to text conversion and text summarization using a medical provider workflow model

2021/8/17

Accented Speech Recognition Inspired by Human Perception

arXiv preprint arXiv:2104.04627

Xiangyun Chu

Elizabeth Combs

Amber Wang

Michael Picheny

2021/4/9

Cascaded multilingual audio-visual learning from videos

arXiv preprint arXiv:2111.04823

Andrew Rouditchenko

Angie Boggust

David Harwath

Samuel Thomas

Hilde Kuehne

...

2021/11/8

Speak or chat with me: End-to-end spoken language understanding system with flexible inputs

arXiv preprint arXiv:2104.05752

Sujeong Cha

Wangrui Hou

Hyun Jung

My Phung

Michael Picheny

...

2021/4/7

Soft-forgetting for connectionist temporal classification based automatic speech recognition

2021/10/26

Diarization of legal proceedings. Identifying and transcribing judicial speech from recorded court audio

arXiv preprint arXiv:2104.01304

Jeffrey Tumminia

Amanda Kuznecov

Sophia Tsilerides

Ilana Weinstein

Brian McFee

...

2021/4/3

Accent-robust automatic speech recognition using supervised and unsupervised wav2vec embeddings

arXiv preprint arXiv:2110.03520

Jialu Li

Vimal Manohar

Pooja Chitkara

Andros Tjandra

Michael Picheny

...

2021/10/7

Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifier

2021/1/26

Text to speech prompt tuning by example

2021/9/9

See List of Professors in Michael Alan Picheny University(New York University)