Blind Room Parameter Estimation Using Multiple Multichannel Speech Recordings

הרקע לפרויקט:

The problem of jointly estimating the total surface area, volume, frequency-dependent reverberation time, and mean surface absorption of a room in a blind manner is studied in this paper. This knowledge of the geometrical and acoustical parameters of a room can be beneficial for applications such as audio augmented reality, speech dereverberation, or audio forensics.The proposed approach utilizes two-channel noisy speech recordings from multiple unknown source-receiver positions.

The proposed model outperforms a recently proposed blind volume estimation method on the considered datasets.

מטרת הפרויקט:

The project focuses on leveraging two-channel noisy speech recordings from multiple unknown source-receiver positions. By developing a novel convolutional neural network architecture that utilizes both single and inter-channel cues, the goal is to accurately estimate the target parameters in a blind manner.

תכולת הפרויקט:

1. Watch the lectures in youtube - Stanford University CS231n, Spring 2017
2. Read the paper
3. Download the dataset
4. Build the model
5. Train the model
6. Expect to satisfactory results :))
The project will be implemented in Pytorch

קורסי קדם:

Deep Learing, Python and Pytorch

דרישות נוספות:

Watching related videos on YouTube

מקורות:

We will implement the following paper:
Blind Room Parameter Estimation Using Multiple Multichannel Speech Recordings