• Applications​​

​​

1. Sentiment analysis of clients for any industry

2. Emotion detection for agent and client for all types of calls

3. Emotional state analysis of a student during oral examination 

4. Agent performance and customer satisfaction (CSat) analysis for promotional calls

5. Sentiment analysis for speakers in online meetings

6. Segregation of clients based on their readiness

7. Sentiment analysis for stress mode in forensic applications

• Application​

​​

1. Speaker segregation for mono audio file recordings.

2. Speaker segregation for forensic applications from suspect audio.

3. Automatic detection of number of speakers in a conference call using unsupervised system. 

4. Diarization and transcription of conference call for speaker audios.

5. Useful for writing minutes of the meeting

• Applications​​

​​

1. Recognizing and verifying suspect person in forensic application

2. Speaker verification for entry in restricted area

3. Speaker verification for bank transactions based on speech

4. Speaker identification as one of the culprits from stored database

5. Speaker verification in case of deep fake generated audio

• Application

​​

1. Useful for call centres

2. Agent performance and score can be found

3. Customer sentiments can be captured

4. Text obtained using speech to text can be used for text processing to do call audits

5. Intelligent algorithm can help actual % of audit

6. Keyword spotting can be used if speech to text is to be eliminated

• Application​

​​

1. Check if any tampering is done by suspect on audio files

2. Check if any phase shift is introduced, or pause is introduced in recording

3. Check if 2 audios recorded on different devices are mixed up

4. Check if any dc shift is introduced

5. Check if original sampling frequency is changed

6. Check the metadata file for the audio

7. Check if a true recording or deep fake audio

1. Convert audio to text. It gives text with punctuation.

2. Use speaker diarization to separate two speaker’s talks.

3. Label agent and client for converted text.

4. Process text as per requirement to generate result in

   excel sheet. It may include identifying certain phrases

   in text.

5. Batch processing is allowed. System uses multi tasking

   environment

1. Developed a system that extracts speech signature or
   voice print for suspect audio.

2. Extracts VAD segments for audio and extracts speaker
   embeddings.

3. Verifies a speaker if the suspect audio matches with the
   control audio.

4. The results obtained excellent

• Application​

​

1. Useful for removing noise from any noisy file

2. Any kind of noise can be removed

3. Useful for forensic domain as well

4. Useful for removing noise from conference calls

5. Possibility of embedding in the form of hardware in head on mic

6. Can be used to measure SNR