# Effects of Number of Filters of Convolutional Layers on Speech Recognition Model Accuracy

arXiv: https://arxiv.org/abs/2102.02326 · HTML: https://mlsanity.com/paper/2102.02326/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 3 Feb 2021.

## Builds on (most cited first, 10 of 10)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [word2vec Parameter Learning Explained](https://mlsanity.com/paper/1411.2738/) (2014)
- [On the Dimensionality of Word Embedding](https://mlsanity.com/paper/1812.04224/) (2018)
- [Wav2Letter: an End-to-End ConvNet-based Speech Recognition System](https://mlsanity.com/paper/1609.03193/) (2016)
- [Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.02720/) (2017)
- [Understand Functionality and Dimensionality of Vector Embeddings: the Distributional Hypothesis, the Pairwise Inner Product Loss and Its Bias-Variance Trade-off](https://mlsanity.com/paper/1803.00502/) (2018)

## Built on by (most cited first, 1 of 1)

- [Searching for Effective Preprocessing Method and CNN-based Architecture with Efficient Channel Attention on Speech Emotion Recognition](https://mlsanity.com/paper/2409.04007/) (2024)

## Abstract (arXiv)

Inspired by the progress of the End-to-End approach [1], this paper systematically studies the effects of Number of Filters of convolutional layers on the model prediction accuracy of CNN+RNN (Convolutional Neural Networks adding to Recurrent Neural Networks) for ASR Models (Automatic Speech Recognition). Experimental results show that only when the CNN Number of Filters exceeds a certain threshold value is adding CNN to RNN able to improve the performance of the CNN+RNN speech recognition model, otherwise some parameter ranges of CNN can render it useless to add the CNN to the RNN model. Our results show a strong dependency of word accuracy on the Number of Filters of convolutional layers. Based on the experimental results, the paper suggests a possible hypothesis of Sound-2-Vector Embedding (Convolutional Embedding) to explain the above observations. Based on this Embedding hypothesis and the optimization of parameters, the paper develops an End-to-End speech recognition system which has a high word accuracy but also has a light model-weight. The developed LVCSR (Large Vocabulary Continuous Speech Recognition) model has achieved quite a high word accuracy of 90.2% only by its Acoustic Model alone, without any assistance from intermediate phonetic representation and any Language Model. Its acoustic model contains only 4.4 million weight parameters, compared to the 35~68 million acoustic-model weight parameters in DeepSpeech2 [2] (one of the top state-of-the-art LVCSR models) which can achieve a word accuracy of 91.5%. The light-weighted model is good for improving the transcribing computing efficiency and also useful for mobile devices, Driverless Vehicles, etc. Our model weight is reduced to ~10% the size of DeepSpeech2, but our model accuracy remains close to that of DeepSpeech2. If combined with a Language Model, our LVCSR system is able to achieve 91.5% word accuracy.