Theo dõi
Siddharth Dalmia
Siddharth Dalmia
Tên khácSid Dalmia
Research Scientist, Google DeepMind
Email được xác minh tại google.com - Trang chủ
Tiêu đề
Trích dẫn bởi
Trích dẫn bởi
Năm
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ...
arXiv preprint arXiv:2403.05530, 2024
13052024
FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
A Conneau, M Ma, S Khanuja, Y Zhang, V Axelrod, S Dalmia, J Riesa, ...
SLT 2022, 2022
3052022
Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding
Y Peng, S Dalmia, I Lane, S Watanabe
ICML 2022, 17627-17643, 2022
1832022
Epitran: Precision G2P for Many Languages
DR Mortensen, S Dalmia, P Littell
LREC 2018, 2018
1792018
Universal phone recognition with a multilingual allophone system
X Li, S Dalmia, J Li, M Lee, P Littell, J Yao, A Anastasopoulos, ...
ICASSP 2020, 2020
1482020
Sequence-based Multi-lingual Low Resource Speech Recognition
S Dalmia, R Sanabria, F Metze, AW Black
ICASSP 2018, 2018
1202018
Espnet-slu: Advancing spoken language understanding through espnet
S Arora, S Dalmia, P Denisov, X Chang, Y Ueda, Y Peng, Y Zhang, ...
ICASSP 2022, 7167-7171, 2022
812022
Transformer-Transducers for Code-Switched Speech Recognition
S Dalmia, Y Liu, S Ronanki, K Kirchhoff
ICASSP 2021, 2021
532021
Robust ASR using neural network based speech enhancement and feature simulation
S Sivasankaran, AA Nugraha, E Vincent, JA Morales-Cordovilla, S Dalmia, ...
ASRU 2015, 2015
532015
Towards Zero-shot Learning for Automatic Phonemic Transcription
X Li, S Dalmia, DR Mortensen, J Li, AW Black, F Metze
AAAI 2020, 2020
43*2020
Llm augmented llms: Expanding capabilities through composition
R Bansal, B Samanta, S Dalmia, N Gupta, S Vashishth, S Ganapathy, ...
arXiv preprint arXiv:2401.02412, 2024
422024
CTC alignments improve autoregressive translation
B Yan, S Dalmia, Y Higuchi, G Neubig, F Metze, AW Black, S Watanabe
EACL 2023, 2022
362022
NoiseQA: Challenge set evaluation for user-centric question answering
A Ravichander, S Dalmia, M Ryskina, F Metze, E Hovy, AW Black
EACL 2021, 2021
342021
Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
S Dalmia, B Yan, V Raunak, F Metze, S Watanabe
NAACL 2021, arXiv: 2105.00573, 2021
342021
On Long-Tailed Phenomena in Neural Machine Translation
V Raunak, S Dalmia, V Gupta, F Metze
EMNLP 2020 Findings, 2020
332020
An approach for self-training audio event detectors using web data
B Elizalde, A Shah, S Dalmia, MH Lee, R Badlani, A Kumar, B Raj, I Lane
EUSIPCO 2017, 2017
29*2017
Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion
S Kim, S Dalmia, F Metze
ACL 2019, 2019
282019
Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
J Lee, A Chen, Z Dai, D Dua, DS Sachan, M Boratko, Y Luan, SMR Arnold, ...
arXiv preprint arXiv:2406.13121, 2024
26*2024
A Study on the Integration of Pre-trained SSL, ASR, LM and SLU Models for Spoken Language Understanding
Y Peng, S Arora, Y Higuchi, Y Ueda, S Kumar, K Ganesan, S Dalmia, ...
SLT 2022, 2022
262022
Multilingual Speech Recognition with Corpus Relatedness Sampling
X Li, S Dalmia, AW Black, F Metze
InterSpeech 2019, 2019
262019
Hệ thống không thể thực hiện thao tác ngay bây giờ. Hãy thử lại sau.
Bài viết 1–20