AIConfPaper
← Search

Samuel Kriman

4 accepted papers

2025

SWAN: An Efficient and Scalable Approach for Long-Context Language Modeling

Krishna C Puvvada, Faisal Ladhak, Santiago Akle Serano, Cheng-Ping Hsieh, Shantanu Acharya, Somshubra Majumdar +5
EMNLP 2025

We present SWAN, a causal Transformer architecture in the decoder-only style that generalizes robustly to sequence lengths substantially longer than those seen during training. SWAN interleaves layers without positional encodings (NoPE) and sliding-window attention layers equipped with rotary positi

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Investigating End-to-End ASR Architectures for Long Form Audio Transcription

Nithin Rao Koluguri, Samuel Kriman, Georgy Zelenfroind, Somshubra Majumdar, Dima Rekesh, Vahid Noroozi +2
ICASSP 2024accepted

This paper presents an overview and evaluation of some of the end-to-end ASR models on long-form audio. We study three categories of Automatic Speech Recognition(ASR) models based on their core architecture: (1) convolutional, (2) convolutional with squeeze-and-excitation, and (3) convolutional mode…

Cited by 0Source ↗Scholar ↗
2023

Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models

Travis M. Bartley, Fei Jia, Krishna C. Puvvada, Samuel Kriman, Boris Ginsburg
ICASSP 2023accepted

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode language discriminatory information in lower layers. Further, w…

Cited by 0Source ↗Scholar ↗
2020

Quartznet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

Samuel Kriman, Stanislav Beliaev, Boris Ginsburg, Jocelyn Huang, Oleksii Kuchaiev, Vitaly Lavrukhin +3
ICASSP 2020accepted

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. I…

Cited by 331Source ↗Scholar ↗