Julian Salazar

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 23

Top Topics

Transfer Learning

Speech Recognition

Keyword Spotting

Top Venues

Trans. Assoc. Comput. Linguistics

Publications

Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, R. J. Skerry-Ryan, Michelle Tadmor Ramanovich
Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM. ICLR (2024)
Jianfeng He, Julian Salazar, Kaisheng Yao, Haoqi Li, Jason Cai
Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training. EACL (1) (2024)
Jianfeng He, Julian Salazar, Kaisheng Yao, Haoqi Li, Jinglun Cai
Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training. CoRR (2023)
Eliya Nachmani, Alon Levkovitch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, R. J. Skerry-Ryan, Michelle Tadmor Ramanovich
LMs with a Voice: Spoken Language Modeling beyond Speech Tokens. CoRR (2023)
Zejiang Hou, Julian Salazar, George Polovets
Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation. Trans. Assoc. Comput. Linguistics 10 (2022)
Zejiang Hou, Julian Salazar, George Polovets
Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation. CoRR (2022)
Ethan A. Chi, Julian Salazar, Katrin Kirchhoff
Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment. NAACL-HLT (2021)
Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith
Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings. CoRR (2020)
Ethan A. Chi, Julian Salazar, Katrin Kirchhoff
Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment. CoRR (2020)
Phillip Keung, Yichao Lu, Julian Salazar, Vikas Bhardwaj
Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings. EMNLP (1) (2020)
Phillip Keung, Yichao Lu, Julian Salazar, Vikas Bhardwaj
On the Evaluation of Contextual Embeddings for Zero-Shot Cross-Lingual Transfer Learning. CoRR (2020)
Phillip Keung, Julian Salazar, Yichao Lu, Noah A. Smith
Unsupervised Bitext Mining and Translation via Self-trained Contextual Embeddings. Trans. Assoc. Comput. Linguistics 8 (2020)
Phillip Keung, Wei Niu, Yichao Lu, Julian Salazar, Vikas Bhardwaj
Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances. CoRR (2020)
Shaoshi Ling, Julian Salazar, Yuzong Liu, Katrin Kirchhoff
BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition. Odyssey (2020)
Shaoshi Ling, Yuzong Liu, Julian Salazar, Katrin Kirchhoff
Deep Contextualized Acoustic Representations for Semi-Supervised Speech Recognition. ICASSP (2020)
Julian Salazar, Davis Liang, Toan Q. Nguyen, Katrin Kirchhoff
Masked Language Model Scoring. ACL (2020)
Toan Q. Nguyen, Julian Salazar
Transformers without Tears: Improving the Normalization of Self-Attention. CoRR (2019)
Julian Salazar, Davis Liang, Toan Q. Nguyen, Katrin Kirchhoff
Pseudolikelihood Reranking with Masked Language Models. CoRR (2019)
Julian Salazar, Katrin Kirchhoff, Zhiheng Huang
Self-attention Networks for Connectionist Temporal Classification in Speech Recognition. ICASSP (2019)
Shaoshi Ling, Yuzong Liu, Julian Salazar, Katrin Kirchhoff
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition. CoRR (2019)
Toan Q. Nguyen, Julian Salazar
Transformers without Tears: Improving the Normalization of Self-Attention. IWSLT (2019)
Shaoshi Ling, Julian Salazar, Katrin Kirchhoff
Contextual Phonetic Pretraining for End-to-end Utterance-level Language and Speaker Recognition. CoRR (2019)
Julian Salazar, Katrin Kirchhoff, Zhiheng Huang
Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition. CoRR (2019)