Database Info

Acted Database

General Information: The final SITB-OSED database contains 12,110 utterances including all five major dialects (Cuttacki, Baleswari, Berhampuri, Sambalpuri, and Phulbani ) spoken by 20 professional Odia native speakers (10 male and 10 female) in Odisha state in India. For each dialect, 4 speakers were performed (2 male and 2 female) with six basic emotions: 1) Anger 2) Surprise 3) Happy 4) Sadness 5) Disgust 6) Fear. The duration of the utterances was vary between 3.5s to 8s. All the samples were recorded in .wav format by 2 channels (stereo), 16-bit quantization rate with a sample rate of 22.05 kHz.

(*Note: This database is for research purposes. To download the complete database please go to the Download SITB-OSED section, )

This acted dataset can be used for the task of Gender identification, speech recognition, Speech-to-Text, etc.

*Additional information: Initially, we collect the acted samples from three dialects including Cuttacki, Baleswari, and Berhampuri which contains 12 professional Odia native speakers (6 males and 6 females) who participated in data recording. The database from these three dialects contains 7317 utterances in comprise with the basics of six emotions: 1) Anger 2) Surprise 3) Happy 4) Sadness 5) Disgust 6) Fear. So far, we have done many experiments using only 7317 samples and published our work in some reputed Journals and Internationals conferences (Link).

Information about the Odia dialects

  • Cuttacki: Cuttacki(Central Odia): Spoken in Cuttack, Jajpur, Jagatsinghpur, Kendrapara, Dhenkanal, Angul, Debagarh and parts of Boudh districts of Odisha with regional variations. The Cuttack variant is known as Katakia.
  • Baleswari: Baleswari (Northern Odia): Spoken in Baleswar, Bhadrak, Mayurbhanj and Kendujhar districts of Odisha and southern parts of undivided Midnapore of West Bengal. The variant spoken in Baleswar is called Baleswaria.
  • Berhampuri: Ganjami (Southern Odia): Spoken in Ganjam, Gajapati and parts of Kandhamal districts of Odisha, Srikakulam district of Andhra Pradesh. The variant spoken in Berhampur is also known as Berhampuria.
  • Sambalpuri: Sambalpuri (Western Odia): It is the western dialect/variety of Odia language with the core variant spoken in Sambalpur, Jharsuguda, Bargarh, Balangir and Subarnapur districts, along with parts of Nuapada and western parts of Boudh districts of Odisha. Also spoken in parts of Raigarh, Mahasamund and Raipur districts of Chhattisgarh.
  • Pulbani: Phulbani Odia: spoken in Kandhamal and in parts of Boudh district.

Sample of acted data

Cuttacki Anger
Cuttacki happy
Cuttacki Sad
Bherhampuri Fear
Bherampuri Disgust
Baleswari Surprise

Spontaneous Database

** We aim to build a very larger-scale spontaneous database (Status: Ongoing)

**We make the spontaneous database publicly available once collection and pre-process completed

General Information: Presently, the Spontaneous Odia speech Emotion database (OSED) consists of 31,000 samples containing the emotional carrier of seven states: happy, anger, sad, disgust, fear, surprise, and neutral. Speech samples were collected from natural discussions in Odia TV programs. We have focused mainly on the materials from shows presenting political, personal, TV serials, and social problems. The reactions and feelings presented by the participants of such programs seem spontaneous and provoked by events and discussions.

Speech recordings or dialogues were segmented manually by using Audacity and Praat software into utterances. The labeling process is divided into two parts. First, the recordings are divided into seven groups of emotions. The division is performed with the use of video material which allows access not only to voice and semantics but also to the visual display of emotions, such as gestures or facial expressions. In the second part of the process, we have labeled the samples based on audio input only.

This emphasizes how subjective the perception of emotions is. We have chosen some volunteers primarily from Silicon Institute of Technology, Bhubaneswar, and some from Utkal University Bhubaneswar. The task is to assess the recordings and classify them into seven emotions.

Sample of spontaneous data

Cuttcaki Anger
Cuttacki Neutral