Efficient Speech Representation Learning with Low-Bit Quantization

• URL: http://arxiv.org/abs/2301.00652v1
• Date: Wed, 14 Dec 2022 06:09:08 GMT
• Title: Efficient Speech Representation Learning with Low-Bit Quantization
• Authors: Ching-Feng Yeh, Wei-Ning Hsu, Paden Tomasello, Abdelrahman Mohamed
• Abstract summary: We apply and investigate recent quantization techniques on speech representation learning models. With aggressive quantization to 1 bit, we achieved 86.32% storage reduction (184.42 -> 25.23), 88% estimated runtime reduction (1.00 -> 0.12) with increased word error rate (7.06 -> 15.96). In comparison with DistillHuBERT which also aims for model compression, the 2-bit configuration yielded slightly smaller storage (35.84 vs. 46.98), better word error rate (12.68 vs. 13.37) and more efficient runtime estimated (0.15 vs. 0.73)
• Score: 32.75829498841329
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the development of hardware for machine learning, newer models often come at the cost of both increased sizes and computational complexity. In effort to improve the efficiency for these models, we apply and investigate recent quantization techniques on speech representation learning models. The quantization techniques were evaluated on the SUPERB benchmark. On the ASR task, with aggressive quantization to 1 bit, we achieved 86.32% storage reduction (184.42 -> 25.23), 88% estimated runtime reduction (1.00 -> 0.12) with increased word error rate (7.06 -> 15.96). In comparison with DistillHuBERT which also aims for model compression, the 2-bit configuration yielded slightly smaller storage (35.84 vs. 46.98), better word error rate (12.68 vs. 13.37) and more efficient estimated runtime (0.15 vs. 0.73).

Related papers

• QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection [57.019527599167255]
  Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. We show in our paper that directly applying quantization in BEV tasks will 1) make the training unstable, and 2) lead to intolerable performance degradation. Our method QD-BEV enables a novel view-guided distillation (VGD) objective, which can stabilize the quantization-aware training (QAT) while enhancing the model performance.
  arXiv  Detail & Related papers  (2023-08-21T07:06:49Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Binary and Ternary Natural Language Generation [24.295815261826153]
  Ternary and binary neural networks enable multiplication-free computation. They promise multiple orders of magnitude efficiency gains over full-precision networks. However, such networks have proven very difficult to optimize. We show first ternary and binary transformer models on the downstream tasks of summarization and machine translation.
  arXiv  Detail & Related papers  (2023-06-02T18:01:02Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Hyperspherical Quantization: Toward Smaller and More Accurate Models [17.154801913113566]
  Vector quantization aims at reducing the model size by indexing model weights with full-precision embeddings. Binary and other low-precision quantization methods can reduce the model size up to 32$times$, however, at the cost of a considerable accuracy drop. We propose an efficient framework for ternary quantization to produce smaller and more accurate compressed models.
  arXiv  Detail & Related papers  (2022-12-24T04:42:15Z)
• The case for 4-bit precision: k-bit Inference Scaling Laws [75.4335600212427]
  Quantization methods reduce the number of bits required to represent each parameter in a model. The final model size depends on both the number of parameters of the original model and the rate of compression. We run more than 35,000 zero-shot experiments with 16-bit inputs and k-bit parameters to examine which quantization methods improve scaling for 3 to 8-bit precision.
  arXiv  Detail & Related papers  (2022-12-19T18:48:33Z)
• Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras [62.70541164894224]
  We introduce several architecture choices which allow us to scale the depth and complexity of such models while maintaining low computation. Our method runs 3.7 times faster than a dense graph neural network, taking only 8.4 ms per forward pass.
  arXiv  Detail & Related papers  (2022-11-22T15:14:20Z)
• SQuAT: Sharpness- and Quantization-Aware Training for BERT [43.049102196902844]
  We propose sharpness- and quantization-aware training (SQuAT) Our method can consistently outperform state-of-the-art quantized BERT models under 2, 3, and 4-bit settings by 1%. Our experiments on empirical measurement of sharpness also suggest that our method would lead to flatter minima compared to other quantization methods.
  arXiv  Detail & Related papers  (2022-10-13T16:52:19Z)
• 4-bit Conformer with Native Quantization Aware Training for Speech Recognition [13.997832593421577]
  We propose to develop 4-bit ASR models with native quantization aware training, which leverages native integer operations to effectively optimize both training and inference. We conducted two experiments on state-of-the-art Conformer-based ASR models to evaluate our proposed quantization technique. For the first time investigated and revealed the viability of 4-bit quantization on a practical ASR system that is trained with large-scale datasets.
  arXiv  Detail & Related papers  (2022-03-29T23:57:15Z)
• Training with Quantization Noise for Extreme Model Compression [57.51832088938618]
  We tackle the problem of producing compact models, maximizing their accuracy for a given model size. A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator. In this paper, we extend this approach to work beyond int8 fixed-point quantization with extreme compression methods.
  arXiv  Detail & Related papers  (2020-04-15T20:10:53Z)
• Attention based on-device streaming speech recognition with large speech corpus [16.702653972113023]
  We present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus. We attained around 90% of a word recognition rate for general domain mainly by using joint training of connectionist temporal classifier (CTC) and cross entropy (CE) losses. For on-demand adaptation, we fused the MoChA models with statistical n-gram models, and we could achieve a relatively 36% improvement on average in word error rate (WER) for target domains including the general domain.
  arXiv  Detail & Related papers  (2020-01-02T04:24:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.