Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Sarı, Leda"'
Autor:
Kang, Wonjune, Jia, Junteng, Wu, Chunyang, Zhou, Wei, Lakomkin, Egor, Gaur, Yashesh, Sari, Leda, Kim, Suyoun, Li, Ke, Mahadeokar, Jay, Kalinli, Ozlem
As speech becomes an increasingly common modality for interacting with large language models (LLMs), it is becoming desirable to develop systems where LLMs can take into account users' emotions or speaking styles when providing their responses. In th
Externí odkaz:
http://arxiv.org/abs/2410.01162
Autor:
Xie, Jiamin, Li, Ke, Guo, Jinxi, Tjandra, Andros, Shangguan, Yuan, Sari, Leda, Wu, Chunyang, Jia, Junteng, Mahadeokar, Jay, Kalinli, Ozlem
Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several rounds of pruning and re-training needed to be run for each language.
Externí odkaz:
http://arxiv.org/abs/2309.13018
Autor:
Sharma, Roshan, Kim, Suyoun, Lazar, Daniel, Le, Trang, Shrivastava, Akshat, Ahn, Kwanghoon, Kansal, Piyush, Sari, Leda, Kalinli, Ozlem, Seltzer, Michael
Spoken semantic parsing (SSP) involves generating machine-comprehensible parses from input speech. Training robust models for existing application domains represented in training data or extending to new domains requires corresponding triplets of spe
Externí odkaz:
http://arxiv.org/abs/2309.09390
Autor:
Le, Matthew, Vyas, Apoorv, Shi, Bowen, Karrer, Brian, Sari, Leda, Moritz, Rashel, Williamson, Mary, Manohar, Vimal, Adi, Yossi, Mahadeokar, Jay, Hsu, Wei-Ning
Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generativ
Externí odkaz:
http://arxiv.org/abs/2306.15687
Autor:
Liu, Shuo, Sarı, Leda, Wu, Chunyang, Keren, Gil, Shangguan, Yuan, Mahadeokar, Jay, Kalinli, Ozlem
This paper presents a method for selecting appropriate synthetic speech samples from a given large text-to-speech (TTS) dataset as supplementary training data for an automatic speech recognition (ASR) model. We trained a neural network, which can be
Externí odkaz:
http://arxiv.org/abs/2306.00998
A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped further the
Externí odkaz:
http://arxiv.org/abs/2303.12197
Autor:
Klumpp, Philipp, Chitkara, Pooja, Sarı, Leda, Serai, Prashant, Wu, Jilong, Veliche, Irina-Elena, Huang, Rongqing, He, Qing
The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an accent-conversion mo
Externí odkaz:
http://arxiv.org/abs/2303.00802
Autor:
Kreyssig, Florian L., Shi, Yangyang, Guo, Jinxi, Sari, Leda, Mohamed, Abdelrahman, Woodland, Philip C.
Self-supervised learning via masked prediction pre-training (MPPT) has shown impressive performance on a range of speech-processing tasks. This paper proposes a method to bias self-supervised learning towards a specific task. The core idea is to slig
Externí odkaz:
http://arxiv.org/abs/2211.02536
Autor:
Liu, Chunxi, Picheny, Michael, Sarı, Leda, Chitkara, Pooja, Xiao, Alex, Zhang, Xiaohui, Chou, Mark, Alvarado, Andres, Hazirbas, Caner, Saraf, Yatharth
It is well known that many machine learning systems demonstrate bias towards specific groups of individuals. This problem has been studied extensively in the Facial Recognition area, but much less so in Automatic Speech Recognition (ASR). This paper
Externí odkaz:
http://arxiv.org/abs/2111.09983
Autor:
Grauman, Kristen, Westbury, Andrew, Byrne, Eugene, Chavis, Zachary, Furnari, Antonino, Girdhar, Rohit, Hamburger, Jackson, Jiang, Hao, Liu, Miao, Liu, Xingyu, Martin, Miguel, Nagarajan, Tushar, Radosavovic, Ilija, Ramakrishnan, Santhosh Kumar, Ryan, Fiona, Sharma, Jayant, Wray, Michael, Xu, Mengmeng, Xu, Eric Zhongcong, Zhao, Chen, Bansal, Siddhant, Batra, Dhruv, Cartillier, Vincent, Crane, Sean, Do, Tien, Doulaty, Morrie, Erapalli, Akshay, Feichtenhofer, Christoph, Fragomeni, Adriano, Fu, Qichen, Gebreselasie, Abrham, Gonzalez, Cristina, Hillis, James, Huang, Xuhua, Huang, Yifei, Jia, Wenqi, Khoo, Weslie, Kolar, Jachym, Kottur, Satwik, Kumar, Anurag, Landini, Federico, Li, Chao, Li, Yanghao, Li, Zhenqiang, Mangalam, Karttikeya, Modhugu, Raghava, Munro, Jonathan, Murrell, Tullie, Nishiyasu, Takumi, Price, Will, Puentes, Paola Ruiz, Ramazanova, Merey, Sari, Leda, Somasundaram, Kiran, Southerland, Audrey, Sugano, Yusuke, Tao, Ruijie, Vo, Minh, Wang, Yuchen, Wu, Xindi, Yagi, Takuma, Zhao, Ziwei, Zhu, Yunyi, Arbelaez, Pablo, Crandall, David, Damen, Dima, Farinella, Giovanni Maria, Fuegen, Christian, Ghanem, Bernard, Ithapu, Vamsi Krishna, Jawahar, C. V., Joo, Hanbyul, Kitani, Kris, Li, Haizhou, Newcombe, Richard, Oliva, Aude, Park, Hyun Soo, Rehg, James M., Sato, Yoichi, Shi, Jianbo, Shou, Mike Zheng, Torralba, Antonio, Torresani, Lorenzo, Yan, Mingfei, Malik, Jitendra
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers f
Externí odkaz:
http://arxiv.org/abs/2110.07058