Evaluate the performance of Google Web Speech API.
(a) Read How Speech Recognition Works.txt which includes 24 sentences, and record your speech as separate WAV(PCM) files using the nomenclature ‘Group ID-Native
Language-gender-Sent#.wav’. For instance, 01-English-female-Sent01.wav. I recommend you to use Audacity to record and edit your speech.
(b) Upload all audio files to ‘BeachBoard - Discussions - Lab - How SpeechRecognition Works’ by clicking ‘Start a New Thread’. Write your Group ID at the subject line and attach the audio files.
(c) Complete the read original method that imports a text file into a list of strings, self.original, in the order of the sentence number.
(d) Refer this site, and complete the conv audio method that converts audio files into a list of strings, self.recognized. The method should convert all audio files (.wav) in the folder, inDir, in the order of Sent#.
(e) Complete the comp string method that compares two lists of strings, self.original and self.recognized, and calculates the similarities of two strings by using Levenshtein Distance. (You need to convert the strings into the lists of words. For instance, ‘I love AI’ to [‘I’, ‘love’, ‘AI’]. Please refer this site.) This method should store the separate similarity scores in self.similarity in the order of Sent#.
(f) Visit ‘BeachBoard - Discussions - Lab - How Speech Recognition Works’ again, andselect two other threads than yours which include;
• the same native language but distinct gender of yours
• distinct native language but same gender of yours
(g)Write a report which includes comparison results using box-and-whisker plots by native languages and genders as shown in Figure 1 and Figure 2. You may use Seaborn, Pandas, or Matplotlib to draw the plots.
Figure 1: An example of the comparison by native languages
